LIST OF TAGS
- agentic ai215
- ai co-scientist53
- ai for science109
- algorithms12
- artificial general intelligence1108
- big data688
- bioinformatics27
- computer graphics69
- data management232
- design patterns104
- developments2
- drug discovery125
- foundation models19
- graph mining448
- language models1
- liberal arts122
- machine learning1577
- parallel computing65
- physical ai2
- protein engineering41
- technology roadmapping22
- world models69
agentic ai
- » Harness-of-Harness: Multi-Day Autonomous Software Development
- » From Foundation Models to Closed-Loop Adaptive Systems
- » Reliable AI Co-Scientists for Drug Discovery
- » GPT-6 Astra System Card
- » Agentic Discovery of Executable World Representations
- » AI 2027: Anatomy of a Forecasted Intelligence Explosion
- » Joint Harness-Weight Optimization for Agentic Language Models
- » OmniTable: The AI-Ready Data Substrate
- » Agentic Knowledge Workflows, and Production-Ready AI
- » WikiSkill: Persistent Knowledge and Transferable Skills
- » VLDB 2026 Data Systems Watch: The Rise of Agentic Data Systems
- » Genesis-Science-1
- » DOE Genesis Mission Phase I
- » Claude Fable 5.1 & Mythos 5.1
- » Recuris: Recursive Experiential–Working Memory Evolution
- » Evidence-Verifiable Autonomous Mission-to-Portfolio Intelligence
- » Execution-Grounded Institutional Co-Strategists
- » Code World Model: Coding Agent as World Brain
- » Ten Principles of AI Agent Economics
- » Agentic Hit Discovery: The First Phase for Agentic AI Drug Discovery
- » The Future of RAG
- » An Economy of AI Agents
- » Agentic AI Drug Discovery Platform: An Implementation Blueprint
- » Vecura and the Rise of Agentic AI Co-Scientists
- » Prime Agent: A Self-Improving RLM Harness
- » Knowledge-Enhanced RAG
- » Harness Engineering: Who designs the harness of the next generation?
- » Graph Engineering in the Era of LLM Agents
- » Multimodal RAG
- » Apodex 1.1: Scaling Agentic Intelligence for Complex Work
- » VLDB 2026: From Text-to-SQL to Provenance-Aware Workflows
- » Epilogue — Reflections on the Journey and Closing Remarks
- » Harness Engineering: How to make ten horses run together
- » Harness Continual Learning
- » From RAG to AI Agents
- » Benchmarking LLM Agents in Algorithmic Design for RSI
- » From AI Co-Scientists to Closed-Loop Drug Discovery
- » Deploying Your Application on the Google Cloud
- » From National Mission to RFP: Mission-Aligned Agentic R&D Planning
- » I-MAP: Institution-Centric Mission-Aligned Agentic R&D Planning
- » Harness Engineering: Ability and memory
- » Evaluating Your RAG Application
- » Choosing the Right Cloud Platform for GenAI Applications
- » Harness Engineering: Proposals and Restrictions
- » The RAG Platform
- » Creating an Intelligent Recommendation System
- » Harness Engineering: Give the AI a map, not an instruction manual
- » Deploying RAG to Production
- » Integrating LangChain4j and Spring AI with Neo4j
- » Harness Engineering: First Harness starting from an empty file
- » Scaling Your RAG Stack
- » Tracing the Course of the Agentic AI Journey
- » Constructing a Recommendation Graph with H&M
- » Harness Engineering: From empty files to a million users
- » The Base RAG Stack
- » Three Ways of Thinking — ADK · CrewAI · LangGraph
- » Introducing the Neo4j Spring AI and LangChain4j Frameworks
- » Harness Engineering: Kent Beck's CLAUDE.md
- » Introduction to Retrieval Augmented Generation (RAG)
- » From Solo to Team — Multi-Agent Loan Processing Practice
- » Exploring Advanced Knowledge Graph Capabilities with Neo4j
- » Harness Engineering: Same model, different harness
- » Richard Sutton's Bitter Lessons and Continuous Learning
- » The 90-Day Playbook: From Framework to Production
- » Doing It All Myself — Single Agent Loan Processing Practice
- » Science does not end with a single correct answer.
- » Training AI Scientists to Replicate Research
- » Adding AI-Powered Search with Haystack
- » Harness Engineering: Stripe Minions
- » Healthcare and Legal RAG: Two More Production Case Studies
- » Where to Start — Practical Roadmap by Maturity Level
- » Building a Movie Knowledge Graph with Neo4j
- » Harness Engineering: Let AI verify AI
- » Financial Compliance RAG: A Production Case Study
- » Advanced adaptation patterns for creating learning agents
- » Building Knowledge Graph Foundations
- » Harness Engineering: One mistake, one rule
- » RAGOps: Versioning, Deployment, and Continuous Improvement
- » System-Level Pattern Net for Operational Readiness
- » Demystifying RAG
- » Harness Engineering: A million lines of code written
- » RAG FinOps: Cost Engineering for Production Retrieval
- » One pattern per agency — five agent-level patterns
- » Introducing LLMs, RAGs, and Knowledge Graphs
- » Harness Engineering: The less, the stronger
- » Analyzing Text Data with Deep Learning
- » Retrieval Observability and Debugging Pipelines
- » Who Calls Whom — Five Human-Agent Interaction Patterns
- » Harness Engineering: Five components of a harness
- » Chemical Structures of Key Cancer Drugs
- » Practical Guide to English Speaking for AI Technology Presentations
- » RAG Evaluation: RAGAS, LLM-as-Judge, and Production Metrics
- » Robustness and Fault Tolerance Pattern Sixteen
- » Reflections
- » Harness Engineering: Three namings
- » Multi-Agent RAG: Orchestrating Specialised Retrievers
- » Explainability and regulatory compliance patterns
- » From the era of designing output to the era of designing trajectories
- » Harness Engineering: The relationship between humans and tools
- » Artificial Intelligence in Cancer Medicine
- » Agentic RAG: Self-Correcting and Multi-Hop Patterns
- » Things You Can't Do Alone — Multi-Agent Tuning Pattern Atlas
- » New Modalities of Cancer Treatments
- » Neuro-Symbolic AI — The Path to Verifiable Autonomous Reasoning
- » In-depth analysis from a research strategy perspective
- » What is more important than power is the path it takes
- » GraphRAG: Knowledge Graph-Enhanced Retrieval
- » Agentic AI Architecture: Components and Interactions
- » Neuro-Symbolic AI × LLM Multi-Agent × Knowledge Graphs
- » Biologic Cancer Drugs
- » AI-Ready Data × Knowledge Graph × LLM Multi-Agent
- » Hybrid Search, Reranking, and Query Transformation
- » Spectrum of LLM Adaptation for Agents
- » Trgeted Cancer 3 Therapy: Protein Kinase Inhibitors
- » Chunking, Indexing, and Document Pipeline Design
- » Agent-Ready LLM: Selection, Deployment, Adaptation
- » Chemotherapies Pyrrhic Victory
- » TxGemma·Agentic-Tx Based Hypothesis Generation Agents
- » Vector Search and Embedding Engineering at Scale
- » Enterprise GenAI: Landscape, Maturity, and Agents
- » Drug Development Execution Agent: Design and Implementation
- » TxGemma·Agentic-Tx Research Trends and Research Agenda
- » Case Study-SDBB: AI Drug Development Workflow
- » The Origin of Cancer
- » How Retrieval Actually Works: First Principles for RAG Builders
- » Molecular Docking — A calculation that reads interlocking
- » The RAG Revolution: Why 40% of Naive Pipelines Fail in Production
- » Biomedical Literature Vector DB for Agentic RAG
- » Self-Improvements in Modern Agentic Systems: A Survey
- » Towards Human-Level Autonomous Research via Chain-of-Evidence
- » AdaJEPA: An Adaptive Latent World Model
- » Latent Representation for Discovery in Multiscale Physical Fields
- » With Intelligence Reinforcing Civilization at the Edge of the Singularity
- » The AI Revolution and the Reshaping of the White-Collar Labor Market
- » Our Plan To Merge Chat And Agents
- » ADMET Prediction: The Journey of Molecules Through the Body
- » The Intelligence to Read Molecules as Language
- » Imprinting Human Preferences into Images using RL
- » System Card: Claude Sonnet 5
- » Orca: The World is in Your Mind
- » Agent-as-a-Router: Agentic Model Routing for Coding Tasks
- » AI-based discovery of new therapeutic modal drug candidates
- » PhysisForcing: Physics-Consistent Robot Videos
- » Improved Large Language Diffusion Models
- » Are We Ready For An Agent-Native Memory System?
- » Apple Neural Engine: Architecture, Programming, and Performance
- » Agentic Systems for Sample-Efficient Drug Formulation Design
- » How Transparent is DiffusionGemma?
- » Provenance-Aware Agent: Judging Assay Context with Graph RAG
- » Crystal structure prediction algorithm by AI co-scientists
- » Autodata: An agentic data scientist to create high quality synthetic data
- » LLM Digital Twins for Cognitive Monitoring
- » OpenThoughts-Agent: Data Recipes for Agentic Models
- » Unlimited OCR Works
- » FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
- » Graphic Reachability 2025-2026 Landscape
- » Deep Research Multi-Agent Framework for Physical Sciences
- » Reversal Q-Learning
- » S-Agent: Hierarchical Tool and Dual Memory-Based Spatial Intelligence
- » AI's Way of Thinking: Evolution from 'Words' to 'Numbers'
- » From AGI to ASI: Pathways, Bottlenecks, and Theoretical Frameworks
- » MiniMax Sparse Attention (MSA) Analysis
- » Vulnerabilities and Response Strategies for LLMs in Healthcare
- » Agent Performance Optimization and Model Co-evolution Strategies
- » Technical Specification for Intelligent Agent Transformation in LLM
- » Qualitative Transformation of ChEMBL-based Hit Selection
- » Bebop: Multi-Token Prediction and Rejection Sampling System for LLM
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Self-Harness: Autonomous Environment Optimization
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Agentic Engineering: Spec-Driven Development for Multi-Agent Systems
- » Architectural Shift to Multi-Agent AI Systems
- » Research Methodology Roadmap for Scientific Discovery
- » Graphic Reachability Algorithm for Hit Selection in Drug Discovery
- » Analysis of the Pros and Cons of On-Policy Expression Distillation
- » State-Maintaining Harness-Based Next-Generation Search Agent
- » Future Economy: Understanding General Computer-Used Agents (GCUA)
- » CLADD Framework: Multi-Agent-Based Drug Discovery
- » AlphaProof Nexus: Innovation in AI-based Mathematics Research
- » AI4Science: Autonomous Discovery and Schema Evolution Framework
- » AlphaProof Nexus: AI-based Proof of Mathematical Hard Problems
- » Self-Revising Science Agents via Category Theory
- » SciDataCopilot & Agentic Science
- » How LLMs Map Human Perceptual Geometry
- » Evaluation of the Scientific Discovery Capabilities of AI Agents
- » LocateAnything: One Box at a Time
- » Why Does AI Lie? Mathematical Inevitability of Hallucination
- » HumanEgo: Zero-Shot Robot Learning from Minutes of Egocentric Videos
- » AI Scientist & Co-Scientist
- » Overview of AI Scientist & Co-Scientist
- » Analysis of the Core Algorithms in Agentic AI Researcher
- » Wet-Lab Automation for AI-Based Drug Development
- » Biology-Inspired AI & Organic Learning
- » Multimodal RAG and Simulator Integration Architecture
- » AI-based Autonomous Scientific Discovery
- » AI Scientist and AI Co-Scientist
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
- » Agentic AI and the Rise of World Models
- » Safety Challenges and Solutions of Recursive Self-Improvement
- » Episodic Memory-Based Continual Learning in Science-Specific LLMs
- » LLM Research Specialized for New Drug Development
- » Research Trends in Simulator-Linked Agent RAG Architecture
- » SIRA: Superintelligent Retrieval Agent
- » Software 3.0 Roadmap: From Vibe Coding to Agentic Engineering
- » ARA-based R&D Roadmap for Maximizing AI Research Productivity
- » Autonomous Agent Systems and Governance in the AGI Era
- » Breaking Technical Thresholds and Securing Business Supremacy
- » Strategic Framework for Agentic World Modeling
- » Integrating ChEMBL with TxGemma and Agentic-Tx
- » Agentic AI for Materials Design
- » A Paradigm Shift In New Drug Development
- » Innovations in Agentic AI and Materials Design
- » The social evolution of AI agents
- » The Nature and Future of Agentic RAG in AI Co-Scientist
ai co-scientist
- » From Traceable SBDD to RNA Foundation Tools
- » From Evidence Lineage to Scientific Self-Audit
- » From Multi-Model Collaboration to Enterprise Drug Discovery
- » Causally Revisable Epistemic Neuro-Symbolic Co-Scientist
- » From Plausible Correlations to Falsifiable Scientific Beliefs
- » Experience-Grounded Drug-Discovery AI Co-Scientist
- » Evidence-Verifiable Autonomous Mission-to-Portfolio Intelligence
- » From Co-Folding Accuracy to Physics-Grounded Agentic Drug Design
- » Execution-Grounded Institutional Co-Strategists
- » Epistemic Molecular World Model for Self-Improving AI Co-Scientists
- » Decision-Centric Epistemic AI Co-Scientist for Drug Discovery
- » Execution-Grounded Multimodal Drug-Discovery Co-Scientist
- » Execution-Grounded Epistemic Neuro-Symbolic Co-Scientist
- » Accelerating Scientific Research with Gemini in the Real-World
- » Self-Improving Experimental AI Co-Scientist for Drug Discovery
- » Epistemic Scientific Autonomy: Molecular LLM Agents and K-Bench
- » Five Shifts Toward Evidence-Grounded Closed-Loop Discovery
- » A Multi-Agent System for Automating Scientific Discovery
- » Measuring AI Scientists: From Exams to Discovery
- » Spatially Grounded Multiscale World Models for AI Co-Scientists
- » Equation-Discovering Physics-Grounded AI Co-Scientists
- » Neuro-Symbolic Scientific World Models in Drug Discovery
- » Epistemic Hyper-Relational Knowledge Graphs for AI Co-Scientists
- » OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
- » Training AI Scientists to Replicate Research
- » Towards Human-Level Autonomous Research via Chain-of-Evidence
- » AdaJEPA: An Adaptive Latent World Model
- » Latent Representation for Discovery in Multiscale Physical Fields
- » With Intelligence Reinforcing Civilization at the Edge of the Singularity
- » The AI Revolution and the Reshaping of the White-Collar Labor Market
- » Our Plan To Merge Chat And Agents
- » ADMET Prediction: The Journey of Molecules Through the Body
- » The Intelligence to Read Molecules as Language
- » Imprinting Human Preferences into Images using RL
- » System Card: Claude Sonnet 5
- » Orca: The World is in Your Mind
- » PhysisForcing: Physics-Consistent Robot Videos
- » Improved Large Language Diffusion Models
- » Are We Ready For An Agent-Native Memory System?
- » Apple Neural Engine: Architecture, Programming, and Performance
- » Provenance-Aware Agent: Judging Assay Context with Graph RAG
- » Crystal structure prediction algorithm by AI co-scientists
- » Autodata: An agentic data scientist to create high quality synthetic data
- » LLM Digital Twins for Cognitive Monitoring
- » HumanEgo: Zero-Shot Robot Learning from Minutes of Egocentric Videos
- » AI Scientist & Co-Scientist
- » Overview of AI Scientist & Co-Scientist
- » Analysis of the Core Algorithms in Agentic AI Researcher
- » AI Scientist and AI Co-Scientist
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
- » Advancing the Frontiers of Mathematical Discovery
- » AI Co-Mathematician: The New Discovery Logic
ai for science
- » From Scientific Skills to Verified Lab Workflows
- » From Discovery to Epistemic Governance
- » From Evidence Paths to Falsifiable Rules
- » Tri-State Neuro-Symbolic AI Co-Scientist for Drug Discovery
- » From Model Scores to Verifiable Scientific Discovery Systems
- » From Problem Formulation to Representation Construction
- » Operational Einstein Test 2.0
- » Toward an Operational Einstein Test for AGI
- » Genesis-Science-1
- » DOE Genesis Mission Phase I
- » Beyond the Final Answer: Operational Einstein Test
- » Stereochemistry at Tetrahedral Centers
- » From Atoms to Acids: The Structural Language of Organic Chemistry
- » Aromatic Compounds: Resonance, Electrophilic Substitution,...
- » Alkenes, Alkynes, and Reaction Mechanisms
- » Reactions of Alkenes and Alkynes
- » The Structural Logic of Organic Compounds
- » Accelerating Scientific Research with Gemini in the Real-World
- » Measuring AI Scientists: From Exams to Discovery
- » From National Mission to RFP: Mission-Aligned Agentic R&D Planning
- » I-MAP: Institution-Centric Mission-Aligned Agentic R&D Planning
- » OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
- » GFG · Geometric Flow Grounding
- » Bayesian filtering based on generative emulators without training
- » CoEvol-NO: Resonance of states and coordinates
- » Towards Human-Level Autonomous Research via Chain-of-Evidence
- » AdaJEPA: An Adaptive Latent World Model
- » Latent Representation for Discovery in Multiscale Physical Fields
- » With Intelligence Reinforcing Civilization at the Edge of the Singularity
- » The AI Revolution and the Reshaping of the White-Collar Labor Market
- » Our Plan To Merge Chat And Agents
- » ADMET Prediction: The Journey of Molecules Through the Body
- » The Intelligence to Read Molecules as Language
- » Imprinting Human Preferences into Images using RL
- » System Card: Claude Sonnet 5
- » Orca: The World is in Your Mind
- » PhysisForcing: Physics-Consistent Robot Videos
- » Improved Large Language Diffusion Models
- » Are We Ready For An Agent-Native Memory System?
- » Apple Neural Engine: Architecture, Programming, and Performance
- » Provenance-Aware Agent: Judging Assay Context with Graph RAG
- » Crystal structure prediction algorithm by AI co-scientists
- » Autodata: An agentic data scientist to create high quality synthetic data
- » LLM Digital Twins for Cognitive Monitoring
- » Deep Research Multi-Agent Framework for Physical Sciences
- » Reversal Q-Learning
- » S-Agent: Hierarchical Tool and Dual Memory-Based Spatial Intelligence
- » AI's Way of Thinking: Evolution from 'Words' to 'Numbers'
- » From AGI to ASI: Pathways, Bottlenecks, and Theoretical Frameworks
- » MiniMax Sparse Attention (MSA) Analysis
- » Vulnerabilities and Response Strategies for LLMs in Healthcare
- » Agent Performance Optimization and Model Co-evolution Strategies
- » Technical Specification for Intelligent Agent Transformation in LLM
- » Qualitative Transformation of ChEMBL-based Hit Selection
- » Bebop: Multi-Token Prediction and Rejection Sampling System for LLM
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Self-Harness: Autonomous Environment Optimization
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Agentic Engineering: Spec-Driven Development for Multi-Agent Systems
- » Architectural Shift to Multi-Agent AI Systems
- » Research Methodology Roadmap for Scientific Discovery
- » CLADD Framework: Multi-Agent-Based Drug Discovery
- » AlphaProof Nexus: Innovation in AI-based Mathematics Research
- » AI4Science: Autonomous Discovery and Schema Evolution Framework
- » AlphaProof Nexus: AI-based Proof of Mathematical Hard Problems
- » Self-Revising Science Agents via Category Theory
- » Training Sand to Think: Artificial General Intelligence & Future of Physics
- » SciDataCopilot & Agentic Science
- » HumanEgo: Zero-Shot Robot Learning from Minutes of Egocentric Videos
- » AI Scientist & Co-Scientist
- » Overview of AI Scientist & Co-Scientist
- » Analysis of the Core Algorithms in Agentic AI Researcher
- » A New System Architecture for the Era of AI Agents
- » The Pitfalls of Correction and the Inevitability of Hallucination
- » Agent Stack and Self-Evolving Skill Optimization
- » Wet-Lab Automation for AI-Based Drug Development
- » An Intelligent Guide Navigating the World of Scientific Knowledge
- » K-Moonshot: The Massive Collision of AI and Science & Technology
- » Intelligent Anomaly Detection in Industrial Environments
- » Protein Thoughts: The Future of Protein Binding in Four Languages
- » Biology-Inspired AI & Organic Learning
- » Multimodal RAG and Simulator Integration Architecture
- » Meet Lance: Native Unified Multimodal Model
- » AI-based Autonomous Scientific Discovery
- » The Einstein Test: Evaluating Artificial Intelligence’s Potential
- » AI Scientist and AI Co-Scientist
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
- » Agentic AI and the Rise of World Models
- » Safety Challenges and Solutions of Recursive Self-Improvement
- » Episodic Memory-Based Continual Learning in Science-Specific LLMs
- » LLM Research Specialized for New Drug Development
- » Research Trends in Simulator-Linked Agent RAG Architecture
- » Advancing the Frontiers of Mathematical Discovery
- » AI Co-Mathematician: The New Discovery Logic
- » Gemma 4-Based Specialized Models by Scientific Discipline
- » Therapeutic/Biomedical LLM Research Trends
- » Optimizing Scientific Discovery through Evaluation-Driven Scaling
- » Why Current AI Struggles with True Scientific Inquiry?
- » AI Collaboration for a Scientific Future
- » Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
- » AI Co-Scientist CoDHy System
- » Agentic AI for Materials Design
- » Innovations in Agentic AI and Materials Design
- » Next-Generation Agentic AI Co-Scientist
- » The Nature and Future of Agentic RAG in AI Co-Scientist
- » AGI Physics Understanding
- » Scientific Research Automation Platform
- » AI - Opening New Horizons in Scientific Discovery
algorithms
- » The End of Training at Finite Width
- » Residual Learning Through Effective Theory
- » Initializing Deep Learning Theory
- » Information in Deep Learning
- » RG Flow of Preactivations: A Finite-Width Theory of Deep Networks
- » RG Flow of the Neural Tangent Kernel
- » Representation Learning at Finite Width
- » Kernel Learning at Infinite Width
- » Gradient Descent and the Neural Tangent Kernel
- » Criticality, Universality, and the Depth-to-Width Scale in Deep Networks
- » Criticality of the Neural Tangent Kernel
- » Bayesian Learning in Deep Neural Networks
artificial general intelligence
- » Compute-Matched Scaling Laws for MoE Looped Transformers
- » From Discovery to Epistemic Governance
- » Large Language Models as a Cognitive Virus
- » Harness-of-Harness: Multi-Day Autonomous Software Development
- » From Foundation Models to Closed-Loop Adaptive Systems
- » Rethinking KV Cache Eviction for Efficient Reasoning
- » From Model Scores to Verifiable Scientific Discovery Systems
- » GPT-6 Astra System Card
- » AI 2027: Anatomy of a Forecasted Intelligence Explosion
- » From Problem Formulation to Representation Construction
- » Operational Einstein Test 2.0
- » Fast Weight Attention for Continual Learning
- » WikiSkill: Persistent Knowledge and Transferable Skills
- » The Singularity: Fiction or Reality?
- » Toward an Operational Einstein Test for AGI
- » Beyond the Final Answer: Operational Einstein Test
- » Claude Fable 5.1 & Mythos 5.1
- » ReWorld: An Interactive World Model with Long-Horizon Memory
- » Recuris: Recursive Experiential–Working Memory Evolution
- » LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- » Bayesian Uncertainty and AI Architectures for AGI
- » Visual General Intelligence: A White Paper
- » Ten Principles of AI Agent Economics
- » The Future of RAG
- » An Economy of AI Agents
- » Prime Agent: A Self-Improving RLM Harness
- » Knowledge-Enhanced RAG
- » Harness Engineering: Who designs the harness of the next generation?
- » Graph Engineering in the Era of LLM Agents
- » Multimodal RAG
- » Structure-based drug design and explainable AI
- » Apodex 1.1: Scaling Agentic Intelligence for Complex Work
- » Epilogue — Reflections on the Journey and Closing Remarks
- » Harness Engineering: How to make ten horses run together
- » Harness Continual Learning
- » From RAG to AI Agents
- » Graph Neural Networks and Drug Interactions
- » Benchmarking LLM Agents in Algorithmic Design for RSI
- » From LLM-Enabled Databases to Agent-Native Data Systems
- » Deploying Your Application on the Google Cloud
- » Harness Engineering: Ability and memory
- » A Comprehensive Survey on Symbolic Regression
- » Evaluating Your RAG Application
- » Piece-based design and scaffold hopping
- » Choosing the Right Cloud Platform for GenAI Applications
- » Harness Engineering: Proposals and Restrictions
- » The RAG Platform
- » Biopharmaceuticals, Cell and Gene Therapy, and AI
- » Creating an Intelligent Recommendation System
- » Multimodal Multi-Agent AI Co-Scientists for Drug Discovery
- » Harness Engineering: Give the AI a map, not an instruction manual
- » Deploying RAG to Production
- » AI monitoring of clinical outcomes and adverse reactions
- » Integrating LangChain4j and Spring AI with Neo4j
- » Harness Engineering: First Harness starting from an empty file
- » Scaling Your RAG Stack
- » AI Combating Antibiotic Resistance
- » Tracing the Course of the Agentic AI Journey
- » Constructing a Recommendation Graph with H&M
- » Harness Engineering: From empty files to a million users
- » The Base RAG Stack
- » The Convergence of AI and Quantum Computing — Two Filters
- » Three Ways of Thinking — ADK · CrewAI · LangGraph
- » Introducing the Neo4j Spring AI and LangChain4j Frameworks
- » Harness Engineering: Kent Beck's CLAUDE.md
- » AI Medical Imaging for Precision Drug Design
- » Introduction to Retrieval Augmented Generation (RAG)
- » From Solo to Team — Multi-Agent Loan Processing Practice
- » Exploring Advanced Knowledge Graph Capabilities with Neo4j
- » Harness Engineering: Same model, different harness
- » Richard Sutton's Bitter Lessons and Continuous Learning
- » Selecting Medication using Electronic Medical Records and ML
- » The 90-Day Playbook: From Framework to Production
- » Doing It All Myself — Single Agent Loan Processing Practice
- » Science does not end with a single correct answer.
- » Adding AI-Powered Search with Haystack
- » Harness Engineering: Stripe Minions
- » Large-scale language models and drug target discovery
- » Healthcare and Legal RAG: Two More Production Case Studies
- » Where to Start — Practical Roadmap by Maturity Level
- » Building a Movie Knowledge Graph with Neo4j
- » Building a QA Agent with LangGraph
- » Harness Engineering: Let AI verify AI
- » Patient Stratification and Precision Medicine
- » Financial Compliance RAG: A Production Case Study
- » Advanced adaptation patterns for creating learning agents
- » Building Knowledge Graph Foundations
- » Asking a KG Questions with Natural Language
- » Harness Engineering: One mistake, one rule
- » Alzheimer's Precision Treatment
- » Integrating AI in pharmacovigilance and clinical trial monitoring
- » RAGOps: Versioning, Deployment, and Continuous Improvement
- » System-Level Pattern Net for Operational Readiness
- » Demystifying RAG
- » Knowledge Graph-Powered Retrieval-Augmented Generation
- » Harness Engineering: A million lines of code written
- » The Challenges of Vaccine Development and AI
- » Counterfactual explainability in AI-driven drug discovery
- » Blockchain and AI in drug development
- » RAG FinOps: Cost Engineering for Production Retrieval
- » One pattern per agency — five agent-level patterns
- » Introducing LLMs, RAGs, and Knowledge Graphs
- » Node Classification and Link Prediction with GNNs
- » 'AlphaFold 4' — DeepMind drug spin-off's private AI
- » Harness Engineering: The less, the stronger
- » Conclusion: DuckDB
- » From discovery to global distribution
- » Analyzing Text Data with Deep Learning
- » Bias and transparency in AI and machine learning models for drug design
- » Generative artificial intelligence for de novo drug design
- » Retrieval Observability and Debugging Pipelines
- » Who Calls Whom — Five Human-Agent Interaction Patterns
- » From Knowledge Graphs to Knowledge Lakes
- » Graph Representation Learning and Graph Neural Networks
- » Harness Engineering: Five components of a harness
- » Performance considerations for large datasets
- » AI Accelerating Vaccine Development
- » Chemical Structures of Key Cancer Drugs
- » Practical Guide to English Speaking for AI Technology Presentations
- » Artificial intelligence for drug repurposing
- » An AI and ML tool in cancer drug development and immunotherapy
- » RAG Evaluation: RAGAS, LLM-as-Judge, and Production Metrics
- » Robustness and Fault Tolerance Pattern Sixteen
- » Talking to Your Knowledge Graph
- » Reflections
- » Graph Feature Engineering: Manual and Semiautomated Approaches
- » KLIFS — Can only be compared by measuring with the same ruler
- » Harness Engineering: Three namings
- » Building and deploying data apps
- » Using DuckDB in the Cloud with MotherDuck
- » AI Innovation in Neuroscience
- » AI-powered genomic medicine: Technologies and challenges
- » AI and machine learning for disease pathway modeling
- » Multi-Agent RAG: Orchestrating Specialised Retrievers
- » Explainability and regulatory compliance patterns
- » Semantic Search and Similarity
- » From the era of designing output to the era of designing trajectories
- » Machine Learning on Knowledge Graphs: A Primer Approach
- » Harness Engineering: The relationship between humans and tools
- » Building data pipelines with DuckDB
- » Accessing Remote Data Using DuckDB
- » AI in Cancer Drug Development and Immunotherapy
- » Artificial Intelligence in Cancer Medicine
- » AI in multi-omics integration for precision drug design
- » Leveraging AI for integrating genomics, transcriptomics, and proteomics
- » AI based toxicity prediction: Advancing drug safety and risk assessment
- » Agentic RAG: Self-Correcting and Multi-Hop Patterns
- » Things You Can't Do Alone — Multi-Agent Tuning Pattern Atlas
- » Dependency Knowledge Graphs
- » New Modalities of Cancer Treatments
- » Knowledge-Guided Sequential Decision-Making: General Discussion
- » Neuro-Symbolic AI — The Path to Verifiable Autonomous Reasoning
- » NED with Open LLMs and Domain Ontologies
- » Where are data mining societies heading?
- » In-depth analysis from a research strategy perspective
- » What is more important than power is the path it takes
- » DuckDB in the cloud with MotherDuck
- » Using DuckDB with JupySQL
- » AI Network-based Drug Repurposing
- » AI-powered In silico ADMET modeling and optimization in drug design
- » AI for predicting drug-likeness and bioavailability
- » AI for predicting pharmacokinetics and pharmacodynamics
- » GraphRAG: Knowledge Graph-Enhanced Retrieval
- » Agentic AI Architecture: Components and Interactions
- » Pattern Detection Knowledge Graphs
- » Reward Functions for Scientific Agents
- » Neuro-Symbolic AI × LLM Multi-Agent × Knowledge Graphs
- » Named Entity Disambiguation
- » Biologic Cancer Drugs
- » Integrating with the Python ecosystem
- » Using DuckDB with JSON Files
- » AI-based network pharmacology
- » AI-Ready Data × Knowledge Graph × LLM Multi-Agent
- » AI in molecular screening: Advances, challenges, and future perspectives
- » Hybrid Search, Reranking, and Query Transformation
- » Spectrum of LLM Adaptation for Agents
- » Identity Knowledge Graphs
- » Residual Policy Gradients for Commonsense RL
- » Trgeted Cancer 3 Therapy: Protein Kinase Inhibitors
- » Building Knowledge Graphs with Large Language Models
- » Exploring data without persistence
- » Performing EDA with DuckDB
- » AI-based drug repurposing in precision medicine
- » Metaphors of medicine
- » Ethical implications of AI in precision drug design: A philosophical inquiry
- » Chunking, Indexing, and Document Pipeline Design
- » Agent-Ready LLM: Selection, Deployment, Adaptation
- » Mapping Data with Metadata Knowledge Graphs
- » Making Universal Policies Universal
- » Chemotherapies Pyrrhic Victory
- » Extracting Domain-Specific Knowledge from Unstructured Data
- » TxGemma·Agentic-Tx Based Hypothesis Generation Agents
- » Using DuckDB with Polars
- » Case study of returning docking results to a knowledge graph
- » Moderan Diffusion Language Models
- » AI-based drug repurposing and combination therapy
- » Epistemological challenges in AI-driven drug discovery
- » AI in drug design: A historical and future perspective
- » Vector Search and Embedding Engineering at Scale
- » Enterprise GenAI: Landscape, Maturity, and Agents
- » Graph-Native Machine Learning
- » Drug Development Execution Agent: Design and Implementation
- » TxGemma·Agentic-Tx Research Trends and Research Agenda
- » Case Study-SDBB: AI Drug Development Workflow
- » Play Trajectory Segmentation
- » The Origin of Cancer
- » From Simple Networks to Multisource Integration
- » Scalable Temporal Graph Neural Network Training on Dynamic Graphs
- » Executing SQL queries
- » A Primer on SQL
- » How Retrieval Actually Works: First Principles for RAG Builders
- » Enriching Knowledge Graphs with Data Science
- » Advanced aggregation and analysis of data
- » Algorithms for Knowledge-Guided Sequential Decision-Making
- » Molecular Docking — A calculation that reads interlocking
- » Create Your First Knowledge Graph from Ontologies
- » Distributed Graph Neural Network Training
- » Getting Started with DuckDB
- » Importing Data into DuckDB
- » The RAG Revolution: Why 40% of Naive Pipelines Fail in Production
- » Integrating Knowledge Graphs with Information Systems
- » Mental World Modeling: Theory of Mind for Agents
- » Intelligent Systems: A Hybrid Approach
- » Harness Engineering — Part 5: Experience Engineering
- » Accelerating Computation for Scalable Graph Neural Network Training
- » An introduction to DuckDB
- » Getting Started with DuckDB
- » Loading Knowledge Graph Data
- » Knowledge Graphs and LLMs: A Killer Combination
- » Harness Engineering — Part 4: Practices
- » Reducing Data Transfer for Scalable Graph Neural Network Training
- » Language of Drug Discovery & ChEMBL Field Guide
- » Graph Databases: Cypher - Graph Query Language
- » KDD 2026: Research Papers
- » Harness Engineering — Part 3: Case Studies
- » Preliminaries: Graph Neural Network Training
- » Organizing Principles for Building Knowledge Graphs
- » How to read Mathematics — A study guide
- » Harness Engineering — Part 2: Framework
- » Introduction to Graph Neural Network Training on Large Graphs
- » Introducing Knowledge Graphs
- » Vibe Coding: The Future of Programming
- » Dynamic Query Answering with Neural Symbolic Reasoning
- » Conclusion and Future Directions of Neural Symbolic Reasoning
- » Deep Learning for Code: Towards Human-Centered Coding Agents
- » Harness Engineering — Part 1: Background
- » Ambiguous Entity Matching with Neural Symbolic Reasoning
- » Neural Symbolic Reasoning over Incomplete KG
- » High-Dimensional Learning Dynamics
- » Ambiguous Query Answering with Neural Symbolic Reasoning
- » Symbolic Reasoning for Inconsistency Detection over Complete KG
- » Kimi K3: Open Frontier Intelligence
- » Knowledge Graph Reasoning: Conclusion and Research Frontiers
- » AI as a Tool for Mathematics, Computer Science, and Machine Learning
- » Accurate Query Answering with Symbolic Reasoning over Complete KGs
- » MVGC: Multi-View Hyper-Relational Knowledge Graph Contrastive Learning
- » Incorporating Ontology to Knowledge Graph Reasoning
- » Foundation Models for Structured Data
- » Science: A New Golden Age
- » NOOA: Building LLM Agents in Native Python
- » Logical Rule Learning
- » AI for Physics: Reliable AI for Physics
- » Complex Query Answering
- » Knowledge Graph Completion
- » Connecting Low-Rank Representations in AI
- » Preliminaries on Knowledge Graph and Symbolic Logic
- » What Are Knowledge Graphs?
- » ICML 2026 Workshop: Resource-Adaptive Foundation Model Inference
- » Structured Probabilistic Inference & Generative Modeling
- » New Frontiers in Game-Theoretic Learning
- » ICML 2026 Workshop: Graph Foundation Models
- » Neural Symbolic Knowledge Graph Reasoning: Literature Review
- » Neural Symbolic Knowledge Graph Reasoning: Introduction
- » ICML 2026 Workshop: Generative and Agentic AI for Biology
- » Failure Modes in Agentic AI
- » Biomedical Literature Vector DB for Agentic RAG
- » DataFlow-Harness: Editable LLM Data Pipelines
- » Self-Improvements in Modern Agentic Systems: A Survey
- » ICML 2026 Hypothesis Testing Workshop
- » ICML 2026 Workshop: Generative and Agentic AI for Biology
- » A Research Landscape of Knowledge Graphs in Data-Systems Venues
- » Planning in the Era of Large Language Models
- » Statistical Frameworks for Uncertainty in Agentic Systems
- » Scalable Learning and Optimization for Scalable Multimodal AI Agents
- » AI for Math Workshop: Toward Self-Evolving Scientific Agents
- » Multi-modal Foundation Models and LLMs for Life Sciences
- » Hyper-Relational Knowledge Graphs for LLM/SLM-based Agentic AI
- » Ontology & Knowledge Graphs for LLM/SLM-based Agentic AI
- » Efficient Multimodal Question Answering
- » ICML 2026 Workshop: Memorization in Trustworthy Foundation Models
- » ICML 2026 Workshop: Forecasting as a New Frontier of Intelligence
- » Decision-Making from Offline Data to Online Adaptation
- » ICML 2026 Workshop: Foundations of Deep Generative Models
- » ICML 2026 Human–AI Co-Creativity Research Atlas
- » Research Landscape of Graph Foundation Models
- » Biomolecular Foundation Models
- » Agent-Based Proof Auditing
- » RESEARCH SYNTHESIS: Hyperbolic Graph Neural Networks
- » The Agentic Researcher: Autonomous Research Framework
- » Dual-Control Conversational Agent Evaluation
- » Phenotype-Conditioned Long-Range Communication
- » LLM-based Multi-Agent Collaboration Optimization Framework
- » MAP: Measuring Agents in Production
- » ICML 2026 Poster Session 8
- » ICML 2026 Poster Session 7
- » ICML 2026 Poster Session 6
- » HyperDepth: Hierarchy-Uniformity Equilibrium
- » Code Security Vulnerability Agent Task Automation
- » Quantifying Frontier LLM Capabilities for Container Sandbox Escape
- » Robust Harmful Features Under Jailbreak Attacks
- » From Papers to Runnable Attacks for Reproducible Benchmarking
- » ICML 2026 Poster Session 5
- » ICML 2026 Poster Session 4
- » ICML 2026 Poster Session 3
- » GFG · Geometric Flow Grounding
- » Bayesian filtering based on generative emulators without training
- » Solving Time-Dependent Differential Equations with Physical Dynamics Systems
- » CoEvol-NO: Resonance of states and coordinates
- » Horizon-Free Learning-Rate Schedules with Weight Averaging
- » Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
- » Protein Fold Classification at Scale- Benchmarking and Pretraining
- » Benchmarking and Understanding Memory for Robotic Generalist Policies
- » Exploratory Visual Aesthetic Planning with Large Vision Models
- » Protein Autoregressive Modeling via Multiscale Structure Generation
- » Motion Attribution for Video Generation
- » Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
- » ICML 2026 Poster Session 2
- » ICML 2026 Poster Session 1
- » Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
- » FLIP2: Expanding Protein Fitness Landscape Benchmarks
- » A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
- » CLEAR: Context-Aware Learning for Adaptive Subtitle Removal
- » Unlearning Data at Scale
- » Calibration, Decisions, and Collaboration in Learning
- » Towards Human-Level Autonomous Research via Chain-of-Evidence
- » ICML 2026 Tutorial: Unlearning Data at Scale
- » AdaJEPA: An Adaptive Latent World Model
- » Latent Representation for Discovery in Multiscale Physical Fields
- » With Intelligence Reinforcing Civilization at the Edge of the Singularity
- » The AI Revolution and the Reshaping of the White-Collar Labor Market
- » Our Plan To Merge Chat And Agents
- » ADMET Prediction: The Journey of Molecules Through the Body
- » The Intelligence to Read Molecules as Language
- » Imprinting Human Preferences into Images using RL
- » System Card: Claude Sonnet 5
- » Orca: The World is in Your Mind
- » Agent-as-a-Router: Agentic Model Routing for Coding Tasks
- » AI-based discovery of new therapeutic modal drug candidates
- » PhysisForcing: Physics-Consistent Robot Videos
- » Improved Large Language Diffusion Models
- » Are We Ready For An Agent-Native Memory System?
- » Apple Neural Engine: Architecture, Programming, and Performance
- » Agentic Systems for Sample-Efficient Drug Formulation Design
- » How Transparent is DiffusionGemma?
- » Provenance-Aware Agent: Judging Assay Context with Graph RAG
- » Crystal structure prediction algorithm by AI co-scientists
- » Autodata: An agentic data scientist to create high quality synthetic data
- » LLM Digital Twins for Cognitive Monitoring
- » OpenThoughts-Agent: Data Recipes for Agentic Models
- » Unlimited OCR Works
- » FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
- » Graphic Reachability 2025-2026 Landscape
- » Deep Research Multi-Agent Framework for Physical Sciences
- » Reversal Q-Learning
- » S-Agent: Hierarchical Tool and Dual Memory-Based Spatial Intelligence
- » AI's Way of Thinking: Evolution from 'Words' to 'Numbers'
- » From AGI to ASI: Pathways, Bottlenecks, and Theoretical Frameworks
- » MiniMax Sparse Attention (MSA) Analysis
- » Vulnerabilities and Response Strategies for LLMs in Healthcare
- » Agent Performance Optimization and Model Co-evolution Strategies
- » Technical Specification for Intelligent Agent Transformation in LLM
- » Qualitative Transformation of ChEMBL-based Hit Selection
- » The Evolution and Applications of Selective State-Space Models
- » Bebop: Multi-Token Prediction and Rejection Sampling System for LLM
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Self-Harness: Autonomous Environment Optimization
- » Video World Model Utilizing Latent Spatial Memory
- » Analysis of the 5-Stage Industry Hierarchy of the AI Ecosystem
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Agentic Engineering: Spec-Driven Development for Multi-Agent Systems
- » Architectural Shift to Multi-Agent AI Systems
- » Research Methodology Roadmap for Scientific Discovery
- » Graphic Reachability Algorithm for Hit Selection in Drug Discovery
- » Protein Structure Prediction and the Paradigm Shift in Modern Science
- » Analysis of the Pros and Cons of On-Policy Expression Distillation
- » State-Maintaining Harness-Based Next-Generation Search Agent
- » Future Economy: Understanding General Computer-Used Agents (GCUA)
- » CLADD Framework: Multi-Agent-Based Drug Discovery
- » AlphaProof Nexus: Innovation in AI-based Mathematics Research
- » AI4Science: Autonomous Discovery and Schema Evolution Framework
- » AlphaProof Nexus: AI-based Proof of Mathematical Hard Problems
- » Self-Revising Science Agents via Category Theory
- » A Comprehensive Analysis of Visual Generative Distillation Framework
- » Structural Transformation of Biological Intelligence and Digital Intelligence
- » Agentic RAG: Medical Exploration and Evidence-Based Search Agent
- » Training Sand to Think: Artificial General Intelligence & Future of Physics
- » Cosmos 3: Omnimodal World Models for Physical AI
- » NVIDIA Cosmos 3 & The Rise of Omnimodal World Models
- » Beyond Vibe Coding: The Rise of SDD
- » Evolution from a Collaboration Model to a Mechanical Verification Model
- » Architectural Intelligence: Synergistic AI-Aided Design and MAS
- » Specification-Driven Development
- » Beyond Transformers: Exploring the Architecture Shifts
- » Recursive Flow Matching: Generative Model for Physics Simulation
- » Neural World Models
- » Information Bottleneck Driven Tree-based Policy Optimization
- » Inference-Centric Hardware Specialization and FP4 Computing
- » Bidirectional Evolutionary Exploration for the Self-Evolution of LLMs
- » SciDataCopilot & Agentic Science
- » Hybrid Neural Proxy Model Physicals Acceleration Strategy
- » Next-Generation Robotics Intelligence: VLA vs JEPA
- » Innovation in Gamma-World and Multi-Agent World Modeling
- » AlphaFold-based AI Drug Discovery: Technology Analysis Roadmap
- » Agentic AI New Paradigm
- » TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
- » Qwen-VLA: Universal Robot Agent Analysis Based on VLA Integration
- » Convergence of LLMs and Graph Representation Learning
- » How LLMs Map Human Perceptual Geometry
- » Superintelligence AI Governance and Einstein Test Analysis
- » Evaluation of the Scientific Discovery Capabilities of AI Agents
- » LocateAnything: One Box at a Time
- » Why Does AI Lie? Mathematical Inevitability of Hallucination
- » HumanEgo: Zero-Shot Robot Learning from Minutes of Egocentric Videos
- » Comparative Analysis of LLMs for Automated Question Generation
- » AI Scientist & Co-Scientist
- » Overview of AI Scientist & Co-Scientist
- » Analysis of the Core Algorithms in Agentic AI Researcher
- » A New System Architecture for the Era of AI Agents
- » The Pitfalls of Correction and the Inevitability of Hallucination
- » Agent Stack and Self-Evolving Skill Optimization
- » Wet-Lab Automation for AI-Based Drug Development
- » An Intelligent Guide Navigating the World of Scientific Knowledge
- » K-Moonshot: The Massive Collision of AI and Science & Technology
- » Intelligent Anomaly Detection in Industrial Environments
- » Biology-Inspired AI & Organic Learning
- » Meet Lance: Native Unified Multimodal Model
- » AI-based Autonomous Scientific Discovery
- » The Einstein Test: Evaluating Artificial Intelligence’s Potential
- » AI Scientist and AI Co-Scientist
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
- » Agentic AI and the Rise of World Models
- » Diffusion-Based Adaptive Tokenization Analysis
- » From Coding to Orchestration
- » AI Simulation-Based Technology Innovation Roadmap
- » Protein Structure Tokenization
- » Olympiad-level Reasoning Optimization for 30B-class Models
- » Gemini 3.5 Flash Agent Strategy
- » SU-01: The AI Math Prodigy
- » Drug-Discovery-Specific LLMs
- » LLM Covering the Entire Drug Development Cycle
- » AlphaFold 3 & Agentic Drug Discovery
- » AlphaFold 3 & Computer Graphics Convergence Study
- » Research Trends in Agentic Data Agents for Science-Specific LLMs
- » Autonomous Agentic AI in Drug Discovery
- » Transitioning to AI Power User: Hyper-Gap Practical Prompting
- » Multimodal Medical Data Integration and Interpretable Architecture
- » AlphaFold 3 & LLM Agents
- » Next-Gen Drug Design: AlphaFold 3 & IsoDDE Fusion
- » Drug Discovery LLM: In-depth Analysis Report
- » The Shift in Computing Paradigms and the Evolution of Agentic Systems
- » FST-based LLM Continuous Learning Framework
- » SciDataCopilot: Accelerating AGI-Driven Discovery with an Agentic AI
- » AI Innovation for Exploring Unexplored Biological Systems
- » Sequence-Structure Design and Optimization of Unnatural Enzymes
- » SIRA: Superintelligent Retrieval Agent
- » Redefining Drug Discovery with TxGemma
- » Advancing the Frontiers of Mathematical Discovery
- » AI Co-Mathematician: The New Discovery Logic
- » LLM In-Context Learning & Hyper-Relational Knowledge Graphs
- » HEAVYSKILL: Deep Thinking in Artificial Intelligence
- » Causal Inference AI Innovation in Drug Discovery
- » Co-Intelligence: Navigating the Era of Alien Intelligence
- » Uni-OPD: On-Policy Distillation Optimization Strategy
- » Drug Development Innovation: TxGemma and Hyper-Relational KG
- » Paradigm Shift in Modern Deep Learning Generalization Theory
- » Innovation of Generative Models through DiT-MoE Architecture
- » In-Context Learning & Hyper-Relational Knowledge Graphs
- » Gemma 4-Based Specialized Models by Scientific Discipline
- » The difference between a diary (search) and knowledge (embodiment)
- » Therapeutic/Biomedical LLM Research Trends
- » Evolution of World Models for Robot Policy Learning
- » AI-based National Re-industrialization Strategy
- » The Revolution of Intelligence Compression and Efficiency
- » Depression Patient Simulator Reliability Verification Guide
- » Computer Graphics Research Trends in Drug Development
- » Software 3.0 Roadmap: From Vibe Coding to Agentic Engineering
- » ARA-based R&D Roadmap for Maximizing AI Research Productivity
- » EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks
- » Next-Generation AI Architecture: JEPA vs. GLP
- » MAD Strategy Guidebook
- » Autonomous Agent Systems and Governance in the AGI Era
- » Recurrent Transformer
- » Breaking Technical Thresholds and Securing Business Supremacy
- » Strategic Framework for Agentic World Modeling
- » Reducing LLM Inference Costs via Non-Verbal Latent Reasoning
- » LLM Post-Learning Efficiency and Performance Innovation Strategies
- » OmniVLA-RL: Mixture-of-Transformers(MoT) Architecture
- » Strategic Drug Repurposing Analysis using ChEMBL Mechanism Data
- » Evolution of Intelligence: Beyond Generative AI
- » SIMPLETES: Strategic Scaling Framework for AI-Driven Scientific Discovery
- » Optimizing Scientific Discovery through Evaluation-Driven Scaling
- » Enhancing Robotic Precision and Action through 3D Spatial Intelligence
- » TxGemma-based Agentic AI: Hyper-Relational KG Drug Development
- » ChEMBL Data-Driven AI Drug Development Strategy
- » ChEMBL Database Schema and Drug Discovery Utilization Guide
- » Integrating ChEMBL with TxGemma and Agentic-Tx
- » Public Benchmark Datasets for AI-Driven Drug Discovery
- » Comparative Analysis of AI Models for Drug Discovery
- » DeepSeek-V4: Innovations for High-Efficiency Large-Scale AI
- » DeepSeek-V4 Architecture: 1M Token Context and Reasoning Scaling
- » New Drug Development Research Dataset
- » Why Current AI Struggles with True Scientific Inquiry?
- » Internalization of 'Epistemological Signals'
- » Qwen3.5-Omni: The Evolution of Integrated Intelligence
- » Qwen3.5-Omni: Analysis of Next-Generation Omnimodal Architecture
- » Bioinformatics-Based Structure-Based Drug Design (SBDD)
- » Innovation and Future of AI-Based Lead Optimization
- » Inverse Molecular Design and Future Directions
- » Innovation in AI-Based Drug Development
- » Innovation in Drug Discovery: The AI-Driven Reverse Design Paradigm
- » Strategic Framework of In-Silico Drug Discovery
- » Hit Identification and Virtual Screening
- » Innovation in Target Identification and Validation
- » Why Can't Artificial Intelligence (AI) Have Consciousness?
- » The Era of Recursive Self-Improvement and Artificial Super Intelligence
- » Recent Research Trends in DTI/DTA Prediction
- » Strategic Transition to Programming System Oversight
- » AI-based National Science and Technology Transformation
- » Innovation in National Scientific Research through AI
- » AI for Energy Systems and Innovation
- » Research Trends: Principles of Data Policy Gradient
- » The Evolution of AI: From AlphaGo to AlphaZero
- » Multimodal Drug-Target Prediction (MDTP) - Research Roadmap
- » Temporal Databases: Foundation for Reliable AI
- » Key to Solving Humanity’s Greatest Global Challenges
- » Biomedical Knowledge Graphs with Multi-Modal Graph Construction
- » Biomedical Knowledge Graphs (BKGs) and Agentic AI
- » The Cell's Sophisticated Engine: Understanding Protein Complexes
- » TxGemma: Open Problems and Vision
- » AI's Secret Passage: Understanding Explicit vs. Latent Space
- » AI Collaboration for a Scientific Future
- » TxGemma: Major Tasks in Agentic LLM for Drug Discovery
- » TxGemma: An Efficient Agentic LLM for Therapeutics
- » Bio-Artificial Intelligence & Graph Neural Networks
- » Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
- » Analysis of Agentic AI for Drug and Material Discovery
- » VLDB Submission Strategy for Bio-AI Researchers
- » SIGMOD Strategy for AI Researchers in Bio-Data
- » Intracellular Precision Mechanical Devices
- » The Molecular Machines of Life: Understanding Protein Complexes
- » Protein Complexes and Interaction Networks
- » PivotRL: Efficient Learning Engine for High-Performance AI Agents
- » Bio Research Transition Guide for AI and CS Experts
- » A New Paradigm for Spectroscopic Data Interpretation
- » Spatial Intelligence: A Common Brain for All Physical Bodies
- » The Future of Materials Science: The Convergence of LLM and PINN
- » Nano-scale Material Design: Integration of LLM and ML
- » Autonomous New Material Discovery Paradigm
- » Trends in LLM and Multimodal Model-Based Materials Science
- » Supermemory: Agentic Search and Memory Retrieval
- » SCIENCECLAW + INFINITE: Research Autonomy System Architecture
- » Understanding RLHF and Information-Oriented Search
- » Key Trends In Materials Science: Closed-loop Knowledge Generation
- » Ψ0 (Psi-Zero): From a Human Perspective to Robot Wisdom
- » AI-Based Autonomous Laboratory and Physical World Modeling
- » Key Research Trends Related to AI Co-Scientists for Materials Design
- » The Era of AI and LLM Integration for Materials Science
- » Three Key Issues in the Materials Field
- » The Future of Materials Science: LLM and Multimodal Innovation
- » AI for Materials Discovery
- » Trends in Agentic AI for Material Discovery
- » AI Co-Scientist for Materials Design
- » Key Research Achievements in Agent AI in Materials Design
- » AI Intelligence Explosion: The 4 Stages of the Law of Scaling
- » Transforming Unstructured Paper Data into Knowledge Graphs
- » Data Lineage: A Guide to Transparent Scientific Discovery
- » Autonomous Scientific Discovery via Agent Collaboration
- » Academic Research Innovation Strategy Through Agentic AI
- » Decision Intelligence in Agentic AI for Material Dicovery
- » Agentic AI for Material and Drug Discovery
- » Future of Drug-Target Interaction
- » Medical AI Spatial Inference Task Guide
- » From Stagnant AI to an Evolving 'Agent'
- » A Study Guide to Drug Discovery for CS/AI Researchers
- » AI Factory & Token Economy
- » Mixture of Experts (MoE) in the Scientific Foundation Models
- » An Automation Revolution Breaking Through the Data Limitations
- » AI Co-Scientists' Innovative Research Paradigm
- » An Architecture for Infinite Streaming Spatial Intelligence
- » Understanding 3-Level Computing Systems for Physical AI
- » Innovation and Efficiency Evaluation of Physics-Based World Models
- » The Key to Modern Physics: Gluon Scattering Amplitude
- » The World of 'Differentiable World Models'
- » Graph Neural Networks (GNN) and Differentiable World Models
- » Analysis of Agentic AI in Drug Development vs. Material Discovery
- » Agentic AI-Based Drug Discovery Research Trends
- » The Wright Brothers' Airplane and the Analogy of 'Giant Bird Rearing'
- » Symbolic Regression Research Trends
- » 3D Structure-Preserving Molecular Tokenization
- » A New Paradigm of AI in New Drug Development
- » A Core Guide to Understanding Bio AI with TxGemma
- » MedGemma: New Horizons for Medical AI
- » Drug Discovery Through 3D Molecular Structure-Based Language Models
- » 3D Molecular Structure-Based Language Modeling for Drug Discovery
- » Uncovering the Mysteries of Disease with AI Agents
- » AI for Scientific Discovery: From a Black Box to a Proven Partner
- » Understanding AI Security: GPT-5.4 Security & Training
- » The Future of Drug Development with AI Co-Scientists
- » The process of forming a mental prison
- » 'Consciousness': An Intricate Blueprint That Moves the Mind
- » Chain of World: How Robots 'Think' About The World
- » AI Ethics and Basic Social Governance
- » Longing from an AI Perspective: Engineering & Cognitive Analysis
- » Research Trends in Scientific Foundation Models
- » The Present and Future of Large-Scale Multi-Agent Collaboration
- » Large-scale Multi-Agent Collaboration and the Evolution of Agentic AI
- » An Introductory Guide to 'EvoScientist' That Turns Mistakes into Wisdom
- » EvoScientist: Continuous Evolution AI
- » Electronic Level Property Prediction
- » Beyond the Language Model (LLM) to the Era of the 'World Model'
- » A Magical Stepping Stone to Reviv Forgotten Memories
- » Symbolic Regression (SR) Research Trends
- » Precursor Selection and End-to-End Synthesis Process Design
- » AI that listens to the voices of cells
- » Drug Development Master Plan for CS/AI Researchers
- » Future-oriented Analysis focusing on AI Ethics and Basic Society
- » The Current State of AI and the Journey Toward AGI
- » Agentic AI-based R&D Innovation Strategy
- » Schrödinger Equation Research Trend Report
- » GPT-5 Thinking Series Evolution
- » How to Broaden Your Thinking Horizon
- » Artificial Hivemind: The Open-Ended Homogeneity of Language Models
- » Why do all AIs answer the same way?
- » The Rise of TECH BIO
- » The Blueprint of Life Designed by AI
- » Heterogeneous Agent Collaborative Reinforcement Learning
- » Design of an Agent-Based Drug Development Framework
- » New Findings On Scattering Amplitude
- » A Key Driver of Data Evolution: Knowledge Graphs and MCP
- » Single-minus gluon tree amplitudes are nonzero
- » The Rise of Agentic AI in Biomedicine
- » The Journey to Meaning: Five-Level Hierarchy
- » From Complexity To Structural Necessity
- » Machine Learning Control by Symbolic Regression
- » Theoretical Physics Proof Using GPT-5.2
- » BioProAgent: Self-Correcting Workflow
- » Introduction To Physics-Informed Machine Learning
- » Symbolic Regression Methods Using Genetic Programming
- » AI Co-Scientist CoDHy System
- » The Evolution of Intelligent Memory: Memory Caching
- » Drug Development Using LLM-based Biomedical Knowledge Graphs
- » From Genes to Disease: The SPOKE Knowledge Graph
- » LLM-Based Biomedical Knowledge Graph Mining
- » Opening the Future of New Drug Development by Connecting Data
- » GNN-Based Biomedical Knowledge Graph Mining
- » Agentic AI for Materials Design
- » A Paradigm Shift In New Drug Development
- » What's the Difference Between 'Knowledge' and 'Experience'?
- » Innovations in Agentic AI and Materials Design
- » Analysis of AI Agent Autonomy and Security Threats
- » Next-Generation Agentic AI Co-Scientist
- » The growth of AI and the asymmetry of its economic expansion
- » LLMs Can Learn to Reason Via Off-Policy RL
- » Artificial Intelligence Simulates Human "Longing"
- » Team of Thoughts - Efficient Test-time Scaling of Agentic Systems
- » The Evolution of Context Engineering
- » Metacognition in AI - Multimodal Memory Agents (MMAs)
- » The social evolution of AI agents
- » MemoryArena - Benchmarking Agent Memory
- » Adapting While Learning - The Evolution of AI Scientists
- » Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- » A Sustainable Collaborative Structure
- » A Paradigm Shift in AI Architecture - Team-of-Thoughts
- » Genomic Language Modeling (GLM)
- » Voice Phishing Detection Technologies, Solutions, and Key Markets
- » The Essential Evolution of AI Technology and 2026 Research Trends
- » Multi-View Graph Contrastive Learning for Voice Phishing Detection
- » Emerging Intelligence and Future of Intelligence
- » The Advent of the Intelligent Economy
- » Neuro-Symbolic AI and Contrastive Multi-View Graph Learning
- » From Larger Models To A Smarter Scaling Era
- » A Breakthrough in Graph Representation Learning Through LLMs
- » Minsky's Society of Mind - The New Frontier of AGI
- » New Horizons in Artificial General Intelligence Research
- » Multi-View Graph Represenation Learning
- » Adaptive Augmentation for Contrastive Multi-View GRL
- » Innovations in Multimodal Graph Learning
- » Multi-Agentic AI Governance
- » Spatial Intelligence and World Models
- » Large-Scale Multi-Agent Risk Analysis by AI Co-Scientist
- » A Guide to Governance for Large-Scale AI R&D
- » AlphaFold Neural Network Architecture
- » AlphaFold's Technological Innovations and Principles
- » Paradigm Shift in New Drug Development
- » A Journey to Explore the Essence of AI
- » Risks and Crises in Large-Scale Multi-Agent Systems
- » Multi-Agent Risks and the Future of AI Co-Scientist Systems
- » LabOS - The AI-XR Co-Scientist That Sees and Works With Humans
- » Implementation Examples of the Full Cycle of Bioresearch
- » Next-Generation AI Weather Forecasting Model
- » Agentic AI Co-Scientist - Current Status
- » Essentials of PIML/PINNs for AI Co-Scientists
- » AI Co-Scientist and Fluid-Material Integration PIML
- » Metal Additive Manufacturing (AM) Melt Pool Multiphysics
- » Agentic AI Co-Scientist in the Bio Field
- » AlphaGenome - AI Models for Advancing Genome Understanding
- » Agentic Reasoning for LLMs - Market Outlook
- » Innovative Diffusion LLM - Creating 'One Step at a Time'
- » PaperBanana - Agentic AI Framework for Academic Illustration
- » Modular AI & World Models - The Next Frontier
- » Hippocampus- A Key Inspiration for the Future of AI World Models
- » Generative AI and Agentic AI
- » The Revolution in Autonomous Intelligence in AI
- » The Evolution of Image Based 3D Reconstruction
- » Evolving from Digital Assistants to Autonomous Physical Operators
- » Technology Strategy Roadmap - 3D Spatial Intelligence
- » Prompt Caching - A New Frontier in LLM Inference Efficiency
- » The Difference Between Experience and Data Learning
- » Gaussian World Models
- » The Collision Point Between Technology and Human Behavior
- » Era of Implicit Intelligence
- » The Magic of 3D Spatial Intelligence
- » The Power of Brain Plasticity and Cognitive Maps
- » RLAIF Research Trends for AI Co-Scientist
- » The Evolution of Intelligent Architectures
- » Beyond Transformers - The Evolution of AI Architectures
- » New Horizons in Video-Language Joint Embedding (VL-JEPA)
- » Nature, humans, tools… and now a fourth class
- » Overview of Compositional World Models
- » From Data Reliance to Physical Common Sense
- » Agentic Reasoning for Large Language Models
- » A Key Driver for Next-Generation World Models
- » Foundation World Models - The Future Of Spatial Intelligence.
- » Beyond Intelligence Towards the Era of Autonomous Evolution
- » The Essence of AI and the Thinking Engine of the Future
- » Agentic Reasoning for Large Language Models
- » New horizons in spatial intelligence - World Models
- » Innovative Technologies Leading The World Model Competition
- » World Models - Transformers vs. Spatial Latent Space
- » The New Frontier of Spatial Intelligence
- » Meta-Prompting for AI Co-Scientist
- » World Models for Spatial Intelligence
- » Spatial Intelligence and World Model Frameworks
- » RAG-Based Workflow for AI Co-Scientist
- » The Nature and Future of Agentic RAG in AI Co-Scientist
- » World Models - Intelligence that understands and changes reality
- » Project Genie - New Horizons in Generative AI
- » The AI Revolution in Drug Discovery
- » GLP-1 - A New Frontier in Modern Medicine
- » Neuro-Symbolic AI - Opening new horizons in intelligence
- » World Models - Dissecting the Brain of Intelligent Systems
- » AGI Physics Understanding
- » Scientific Research Automation Platform
- » The Rise of World Models and Spatial Intelligence
- » Open-Ended Learning
- » CES Keynote - Completely Reinventing the Computing Stack
- » Meta-Prompting for AI Co-Scientist
- » AI - Opening New Horizons in Scientific Discovery
- » The Thinking Game
- » Generative AI for Data Synthesis
- » AGI and Consciousness
- » Toward Artificial Metacognition
- » AI for Science and AI for Research
- » AI's Next Breakthroughs, AGI Timeline
- » LLM Agentic Reasoning - Data Perspective
- » NeurIPS 2025 Trends related to AI Co-Scientist
- » LLM Performance Advances - Acceleration Beyond Moore's Law
- » LLM Routing Overview
- » The Data-Driven Reasoning Roadmap
- » Context Caching Concept
- » Summary of Awesome Agentic Reasoning
- » Trends in AI for Science and Technology
- » Google DeepMind’s Demis Hassabis & The Paradox of AI Progress
- » Agentic Reasoning for AI Co-Scientist
- » Agentic AI Prompting for AI Co-Scientist
- » Agentic Design Patterns
- » Reinforcement Learning from AI Feedback
- » Research Trends in Retrieval-Augmented Generation
- » Multimodal RAG Research Trends
- » Multi-Modal Integration AI for AI Co-Scientist
- » Context Engineering, Clearly Explained
- » New Trends in Time-Series Anomaly Detection
- » The New Era of Data and Intelligence
- » Hypothesis Generation for AI Co-Scientist
- » What is a Context Window? Unlocking LLM Secrets
- » RAG & GraphRAG for AI Co-Scientist
- » Automated Experiment Design for AI Co-Scientist
- » The non-technical PM's guide to building with Cursor
- » The Dawn of Autonomous AI - Agentic Reasoning
- » Token Compression Trends
- » Peer Review for AI Co-Scientist
- » Multi-Agent Systems Research Trends
- » Foundational Data Management
- » AI-Ready Data Research Trends
- » Context Engineering for AI Co-Scientist
- » AI Co-Scientist Transforming Biomedical Research
- » Andrew Ng Agentic Reviewer
- » Build a Multi-Agent GenAI System in Minutes
- » Data Engineering from Ingestion to AI-Ready
- » DeepResearchEval
- » Awesome Physical AI
- » Build AI-Ready Data Foundation
- » Anomaly detection in time series with Python
- » Unlock Better RAG & AI Agents with Docling
- » Applying Foundational Models for Time Series Anomaly Detection
- » Joint Embedding Predictive Architecture (JEPA)
- » Cursor AI Tutorial for Beginners
- » Agentic Memory
- » Deep Delta Learning
- » NVIDIA Live with CEO Jensen Huang
- » Mapping LLMs, RAG & AI Agent Frameworks
- » LLM‑D Explained
- » A New Kind of AI Is Emerging And Its Better Than LLMS?
- » The AI Co-Scientist
- » Causal Machine Learning
- » How to use Hugging Face models on VS Code Copilot
- » Mastering ChatGPT's 5.2 New Tools - A Complete Guide
- » CS50x 2026 - Artificial Intelligence
- » How to Stop AI from Killing Your Critical Thinking
- » AI year in review - Trends shaping 2026
- » Build Private Agentic AI Flows with LLMs for Data Privacy
- » Cybersecurity Trends in 2026
- » Multi Agent Systems Explained
- » RAG vs Agentic AI - How LLMs Connect Data for Smarter AI
- » Anatomy of AI Agents
- » AI Trends 2026 - Quantum, Agentic AI & Smarter Automation
- » The Power of Open Source - Building Giants in the Open
- » Adaptation of Agentic AI
- » AI’s Models of the World, and Ours
- » Why LLMs will never get us to AGI
- » Googles AI Boss Reveals What AI In 2026 Looks Like
- » Beyond AI Agents - The Future of Enterprise AI
- » The future of intelligence - Demis Hassabis
- » Memory in the Age of AI Agents
- » Long-horizon Reasoning Agent
- » Relational Visual Similarity
- » Large Causal Models from Large Language Models
- » Tensor Logic "Unifies" AI Paradigms
- » Doing Effective Research
- » Evolving General Cooperation with a Bayesian Theory of Mind
- » Visual Geometry Grounded Transformer
- » Gartner's Top Tech Trends for 2026
- » Unlocking Iterative Reasoning for Any Image Editor
- » Measuring Agents in Production
- » How to secure your AI Agents - A Technical Deep-dive
- » No Vibes Allowed - Solving Hard Problems in Complex Codebases
- » The Heilmeier Catechism
- » Defying Gravity - Kevin Hou, Google DeepMind
- » How to build an AI agent with MCP
- » Balancing Humanity and Technology, HI and AI
- » Mathematics of Continual Learning
- » AlphaFold - Grand challenge to Nobel Prize with John Jumper
- » AlphaEvolve
- » Large Language Models are Good Relational Learners
- » Are Large Language Models Good Temporal Graph Learners?
- » How GPT 5 Solved Unsolved Math Problems
- » Hands on with our new agentic development platform
- » The Godmother of AI on jobs, robots
- » Judea Pearl, 2011 ACM Turing Award Recipient
- » Google’s Gemini 3 - AI agents, reasoning and search mode
- » The Power of AI Agents and Agentic AI Explained
- » Quick introduction to Beam Search
- » Creating AI Ideas for Research
- » How AI Will Cure All Disease
- » A Unified Multi-Agent System for Generalistic Scientific Reasoning
- » Beyond Transformer - Building an Artificial Mind
- » Accelerating New Algorithm Discovery with Language Models
- » Video Generation as a Promising Multimodal Reasoning Paradigm
- » Scaling Agent Learning via Experience Synthesis
- » Social engineering, malware, and the future of cybersecurity
- » Bridging the Data Chasm for the Agents of the Future
- » Generative AI for Enhanced Data Quality in the Era of LLMs
- » The Minds of Modern AI - The AI Vision of the Future
- » The future of autonomous driving with Vincent Vanhoucke
- » Causality from Multi-Modal Data
- » Meaning and Intelligence in Language Models
- » On Reasoning LLMs - Myths, Merits, and How to Move Forward
- » Toward Generalist Humanoid Robots
- » The Free Transformer
- » Test-Time Updates - Next Steps for Robust and Efficient Vision
- » Some intuitions About Large Language Models
- » Extending Moore’s Law with Low-Cost Memory Reliability
- » MGAIC Symposium - Foundations and Futures Keynote
- » Google Researcher Shows Life "Emerges From Code"
- » Key Ideas in AI in 2025
- » Introducing serverless reinforcement learning
- » Don't learn AI Agents without Learning these Fundamentals
- » AI Agents + LLM Reasoning
- » ARC-AGI-3 and Action Efficiency - ARC Prize @ MIT
- » Graph Learning Meets Theoretical Computer Science
- » Reasoning with Sampling - Your Base Model is Smarter Than You Think
- » ACE Agentic Context Engineering - Self-Learning AI
- » How To Get The Most Out Of Vibe Coding
- » Do Vision-Language Models Represent Space and How?
- » Yann LeCun at Duke's Responsible AI Symposium
- » PyReason and Applications
- » Self-Supervised Learning, JEPA, World Models, and the future of AI
- » What Are Vision Language Models?
- » AI Agents and the Next Cybersecurity Challenge
- » The Best AI Vibe Coding Agents
- » Autonomous Functions & Real-World Applications
- » Context Engineering for Agents & Multi-Agent Systems
- » Gemini Makes Llama 3 Doubt Itself (92%)
- » The Eigenvector of Multi Agent Systems w/ RAG
- » AI Nano Bio Agents (ETH)
- » Building Decision Agents with LLMs & Machine Learning Models
- » Agentic AI MOOC
- » How to use GitHub Copilot (the complete beginner's guide)
- » Father of RL thinks LLMs are a dead end
- » Vibe Coding Fundamentals In 33 minutes
- » Agentic AI MOOC
- » The Hardest Challenge in Neurosymbolic AI - Symbol Grounding
- » Beyond Rendering - Why Graphics Are Needed For Physical AI
- » Agent to Agent Interactions with NLIP
- » Accelerating Physical AI Certification With NVIDIA Halos
- » Agentic GraphRAG
- » Model Context Protocol (MCP) Explained
- » AI coding with Gemini CLI - Google's terminal agentic coding tool
- » Reinforcement Learning, Kernels, Reasoning, Quantization & Agents
- » Building Multimodal AI Agents From Scratch
- » The New Code — Sean Grove, OpenAI
- » How to Train Your Agent - Building Reliable Agents with RL
- » Make your LLM app a Domain Expert
- » RAG Agents in Prod - 10 Lessons We Learned
- » AI Ready Data-Forging the Path to Reliable and Scalable AI
- » Test-time Computing
- » Visual CoT Reasoning for Vision-Language-Action Models
- » Gentle Introduction to Absolute Zero
- » High-Fidelity Rendering for Physical AI
- » OpenUSD for Physical AI
- » Scientific Datasets and Large Language Models
- » AI 2027 - A Realistic Scenario of AI Takeover
- » GraphRAG to create optimized LLM context windows
- » Practical GraphRAG - Making LLMs smarter with Knowledge Graphs
- » Architecting Agent Memory - Principles, Patterns ...
- » GraphGeeks Talk - Knowledge Graphs for AI Agents
- » HybridRAG - A Fusion of Graph and Vector Retrieval
- » Graph-Based RAG for Dense Enterprise Knowledge
- » Learn to Build with Gemini Nano-Banana
- » Trimming GraphRAG Complexity
- » Multi-Level Graph Representation Learning
- » Towards Symphonious Integration of Quantization and Graph
- » Generating Synthetic Data for Physical AI With NVIDIA Cosmos
- » Intern-S1 - Multimodal LLM for Science
- » Modeling Nonlinear Complex PDEs with AI
- » How to Use a Knowledge Graph
- » GraphRAG vs. Traditional RAG - Higher Accuracy & Insight with LLM
- » AI Agents - Transforming Anomaly Detection & Resolution
- » AI Retrieval with Knowledge Graphs & Cypher
- » Foundation Models for Robotics
- » Google's AI Co-Scientist Explained
- » Real-time Experiments with an AI Co-Scientist
- » A Vision of SuperIntelligence from Experience
- » Synthetic Data for LLM Fine-Tuning for ACT-R
- » Knowledge Distillation Explanation and Implementation
- » Extract the Knowledge of Graph Neural Networks and Go Beyond it
- » The physics behind diffusion models
- » Building Hyper-Relational Knowledge Graphs
- » Hyper-Relational Knowledge Graphs
- » Introduction to GraphRAG
- » Extracting Knowledge Graphs From Text With GPT4o
- » Causal Knowledge Graph
- » Modelling Humans with Neural Networks for Behavioural Mechanism
- » Virutal Cells - Predict, Explain, Discover
- » Interactive Reasoning Benchmarks - ARC-AGI-3 Preview
- » Heterogeneous Graph Neural Network
- » Heterogeneous graph learning
- » RL Fine-Tuning of LLMs
- » Knowledge Graph Construction Demo from raw text using an LLM
- » Knowledge Graphs, Property Graphs and HyperGraphs
- » Graphs for Causal AI
- » Advanced PyReason Tutorial
- » PPO Implementation from Scratch
- » Knowledge Distillation - Build Smaller, Faster AI Models
- » Uncertainty in LLM Explanations
- » DeepSeek's GRPO (Group Relative Policy Optimization)
- » Learn Ollama in 15 Minutes - Run LLM Models Locally for FREE
- » Knowledge Distillation - How LLMs train each other
- » Batch Normalization (ICML 2025 Test Of Time Award)
- » Proximal Policy Optimization (PPO) for LLMs Explained Intuitively
- » Robust Link Prediction over Noisy Hyper Relational Knowledge Graphs
- » Synthetic Text Generation Tutorial
- » Synthetic Data Generation Using LangChain in 5 Mins!
- » Synthetic Data Generation using LLM
- » Knowledge Graphs, Property Graphs and HyperGraphs
- » Research Trends in Voice Phishing Detection
- » Hyper-Relational Knowledge Graphs
- » AI Agent vs Agentic AI; Understand The Actual Difference
- » Foundations of Neurosymbolic AI
- » Voice Phishing Detection Framework Diagram
- » Towards multimodal foundation models in molecular cell biology
- » Exploring Multi-Agent Risks from Advanced AI
- » Neural Graph Databases
- » Reachability in Voice Phishing Detection
- » AGI and Agentic AI in Voice Phishing Detection
- » Multimodal Large Language Models in Voice Phishing Detection
- » Major Algorithms in Voice Phishing Detection
- » Synthetic Metacognition for Managing Tactical Complexity
- » Multi-Hop Question Answering on Knowledge Graphs
- » GraphRAG Tutorials
- » Scaling GraphRAG; Efficient Knowledge Retrieval for AI
- » NeurIPS 2024; Key AI Trends & Breakthroughs
- » Graph Learning - Principles, Challenges, and Open Directions
- » Physics of Language Models
- » What Leaders Need to Understand About AI
- » NVIDIA CEO Jensen Huang Live GTC Paris Keynote
- » I Tried to Warn Them, But We’ve Already Lost Control!
- » The Future of OpenAI, ChatGPT's Origins, ...
- » Software Is Changing (Again)
- » Agentic AI Design Patterns Introduction and walkthrough
- » Denoising Score Matching for Gaussian Prob. Path
- » Conditional Prob. Path, Vector Field, and Score
- » Action-Minimization Meets Generative Modeling
- » Learning and Reasoning in Neurosymbolic AI
- » LLM Reasoning - Key Ideas and Limitations
- » Causal Reasoning using Multimodal Large Language Models
- » NeuroSymbolic Causal Reasoning for AGI
- » Limitations of Vision-Language Models
- » Neuro-Symbolic AI and AllegroGraph
- » Grounding in Artificial General Intelligence
- » 2025 Trends - Neuro-Symbolic AI
- » Introduction to AI Ready Data Foundation
- » Metacognitive LLM for Scientific Discovery
- » Causal Inference in Python - Theory to Practice
- » How Neuro-Symbolic Approaches Combine the Best of Both Worlds
- » Roadmap to Artificial General Intelligence
- » Controlling Language Models
- » Multimodal Foundation World Models for Generalist Embodied Agents
- » Neuro Symbolic AI
- » Neuro Symbolic AI
- » AI Agents in Action - How Research Agents Solve Complex Problems
- » Inductive Logic Programming with dILP
- » Introduction to Logic for AI
- » Neurosymbolic AI - Evolution and Current state of affairs
- » Symbolic AGI - How the Natural Will Build the Formal
- » What is the "Meta" in Metacognition?
- » Papers related to Logical Neural Networks
- » Neuro-Symbolic Methods for Open-Ended Cooperative AI
- » Reasoning with PyReason
- » Google I/O '25 Keynote
- » Cognitive Tools for Making the Invisible Visible
- » LangChain Mastery in 2025
- » Neurosymbolic Programming
- » Get Started with GitHub Copilot in VS Code 2025
- » Logical Neural Networks; Towards Unifying Statistical and Symbolic AI
- » Google AlphaEvolve
- » Google Just Introduced NEW FORM of Intelligence
- » Neuro-Symbolic AI with AllegroGraph
- » Neuro-Symbolic Concept Learner
- » Towards Causal Foundations of Safe AGI
- » How the Brain Creates Emotions
- » Emotion Intelligence in AGI
- » New "Absolute Zero" Model Learns with NO DATA
- » 10 Things Coming In 2026 (A.I In 2026 Major Predictions)
- » A Survey on Causal Generative Modeling
- » 7 BEST, 100% FREE AI Tools For Research In 2025
- » Navigating Artificial General Intelligence Development
- » Research Topics in Artificial Genearl Intelligence
- » Continuity Equation and Fokker-Planck Equations
- » Bioassays for Proteins, Vitamins and Antibiotics
- » Causality-inspired generative modelling
- » Causal AI & Generative Models
- » Neuro Symbolic Reasoning and Learning
- » LLMs are Greedy Agents
- » DeepSeek-R1 Thoughtology; ＜Thinking＞ about LLM Reasoning
- » Learning, Reasoning, and Planning with Neuro-Symbolic Concepts
- » The Future of Language Models; A Perspective on Evaluation
- » Design of Protein Structure with RFdiffusion
- » Marginal Probability Path
- » Shaping the Future of AI Innovations
- » Energy-Based Models
- » OpenAI’s Sam Altman Talks ChatGPT, AI Agents and Superintelligence
- » Superintelligent Agents Pose Catastrophic Risks
- » An Introduction to NVIDIA Cosmos World Foundational Models
- » Key Research Topics in Artificial General Intelligence
- » GPT 5 — The New AI Era is Here! Features EXPLAINED
- » Gaussian Probability Path
- » Causal AI; Current State-of-the-Art & Future Directions
- » Towards Rational Drug Design with AlphaFold 3
- » Ex-Google CEO's 2026 Warning; AI Will Be Smarter & Uncontrollable
- » Causal AI Agents for Precision Medicine
- » Hopes, fears and predictions for future of AI
- » The brilliance of AlphaFold 3
- » Highly Accurate Protein Structure Prediction with AlphaFold
- » A brief history of protein structure prediction and design
- » This Former OpenAI Employee Just Revealed Everything...
- » Metas AI Boss Says He DONE With LLMS...
- » An Introduction to Flow and Diffusion Models
- » NVIDIA CEO Jensen Huang's Vision for the Future
- » What's next for AI at DeepMind, Google's AI lab
- » Major OpenAI Employee Leaves, Google Prepares For AGI...
- » How AI Cracked the Protein Folding Code and Won a Nobel Prize
- » Pre-Training GPT-4.5
- » Marvin Minsky - The Emotion Machine
- » Geoffrey Hinton - Will AI Save the World or End it?
- » Marvin Minsky - Artificial Intelligence
- » Marvin Minsky; A Society of Minds
- » The Society of Mind
- » Diffusion for World Modeling; Visual Details Matter in Atari
- » OpenAI Surprises Everyone, Superintelligence approaches
- » Yann LeCun & John Werner on The Next AI Revolution
- » South Korean President Yoon Suk Yeol removed from office
- » NEW VISUAL CoT Reasoning
- » Causal-aware machine learning
- » Learning to Predict Global Atrial Fibrillation Dynamics
- » The Heterophilic Graph Learning Handbook
- » How to write Tree of Thoughts Prompts
big data
- » OmniTable: The AI-Ready Data Substrate
- » Temporal Graph Analytics with Architecture-Aware Version Skipping
- » Adaptive Temporal Variable Ordering for Graph Joins
- » Neuro-Symbolic AI × LLM Multi-Agent × Knowledge Graphs
- » AI-Ready Data × Knowledge Graph × LLM Multi-Agent
- » What's the difference between programming and coding
- » Prompt Engineering Overview
- » Cross-Platform Data Lineage with OpenLineage
- » Continuous Training and Deployment with ZenML and Seldon
- » CVPR Highlights 2023
- » Robust and Trustworthy Deep Learning
- » PFNs; Use neural networks for 100x faster Bayesian predictions
- » Multimodal Deep Learning for Protein Engineering
- » Topological Deep Learning; Going Beyond Graph Data
- » Is Distance Matrix Enough for Geometric Deep Learning?
- » Sign and Basis Invariant Networks for Spectral Graph Representation Learning
- » Distributed and Multiagent Reinforcement Learning
- » A Distributional Multi-agent Reinforcement Learning Approach
- » Deploy and Scale Models with BentoML
- » Tool Agnostic MLOps with ZenML
- » The Four Pillars of Machine Learning
- » When to use Kubernetes natively over Kubeflow for ML
- » Deploy ZenML + Kubeflow + MLflow + Minio
- » MLOps Pipeline Tutorial with ZenML and Kubeflow
- » ML models with ZenML and BentoML
- » Recent Advances in Vision Foundation Models
- » CVPR 2023 Tutorials
- » Model Registry and Deployment with MLflow
- » How to Deploy ML Models in Production with BentoML
- » Data Science–A Systematic Treatment
- » LEARN ENGLISH with STEVE JOBS
- » DuckDB Internals
- » How to Master the Art of Leadership
- » Getting Started with ZenML
- » Generative Models for Language and Vision
- » ChatGPT, LLMs & Generative AI; What Your Business Needs to Know
- » Differential Privacy & Variants
- » Towards Learned Database Systems
- » Deep Lake; a Lakehouse for Deep Learning
- » Towards Natural Language Query Answering
- » Do We Still Need People To Write Database Systems?
- » Generative AI and Databases
- » Contrastive Learning in PyTorch
- » Self-Supervised Learning; Self-Prediction and Contrastive Learning
- » Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks
- » Bayesian Neural Network
- » Study Less Study Smart
- » Kubeflow v1.7 Release Overview
- » Amazon Redshift Internals
- » ChatGPT Course – Use The OpenAI API to Code 5 Projects
- » Installing and Using NVIDIA Docker
- » Hypertree Decompositions
- » What is Platform Engineering?
- » Databricks Spark SQL / Photon
- » Google BigQuery / Dremel
- » Personalized Image Generation
- » Kubeflow Pipelines 2.0
- » Learning to Transfer Knowledge Through Embedding Spaces
- » Traffic Prediction with Transfer Learning
- » First-Passage Percolation and Related Models
- » Sparse Fourier Transform Algorithm for Real-Time Applications
- » The Frontier of Deep Learning for Robotics
- » Microsoft's Products Will Soon Access Open AI Tools Like ChatGPT
- » LLaMA & Alpaca; "ChatGPT" On Your Local Computer
- » Multi-Objective Recommender Systems
- » Hands-on Explainable Recommender Systems with Knowledge Graphs
- » Improving Recommender Systems with Human in the Loop
- » Open-Source Systems for Federated Learning
- » An Introduction to Federated Computation
- » Data Governance and Sharing on Lakehouse
- » Data Mesh and Lakehouse
- » Master Data Management
- » Setting up Big Data Fabric
- » On Future of the Modern Data Stack
- » Data Virtualization in Data Fabric
- » Recommender Systems using Graph Neural Networks
- » Activate Your Modern MetaData Stack
- » Databricks Lakehouse makes payments ingestion and analytics simple
- » The Essential Guide to Data Lineage
- » Data Governance Explained in 5 Minutes
- » Automated Data Lineage with Unity Catalog
- » Active Metadata - Understanding the magic behind the Data Fabric
- » Introduction to Data Mesh
- » PostgreSQL vs MySQL
- » Activate Your Metadata to Empower Innovation
- » Accelerating Hybrid Data Mesh Implementation
- » Deep-Dive into Delta Lake
- » Delta Lake 2.0 Overview
- » Advancing Spark - The Photon Whitepaper
- » Column-Level Lineage and Active Metadata
- » Five Things to Consider About Data Mesh and Data Governance
- » Data Mesh Implementation Patterns
- » Intro to Databricks Lakehouse Platform Architecture and Security
- » Meshing About with Databricks
- » Enterprise Data Fabric
- » Data Fabric for Self-Driving Cars
- » Speed at Scale - Using GPUs to Accelerate Analytics for Extreme Use Cases
- » SpatialHadoop - A MapReduce Framework for Big Spatial Data
- » Real-Time Data Processing with Apache Flink
- » Mesos Installation
- » Building Mesos
- » An Introduction to Protobufs
- » Taking the I out of PaaS with Apache Mesos
- » Software Projects Built on Mesos
- » Distributed Deep Learning on Mesos
- » Apache Mesos and GPUs
- » Introduction to Graph Thinking
- » Advanced Analytics with Spark
- » Mining Massive Data Sets
- » Reinforcement Learning Course - Georgia Tech
- » Digital Transformation in a Connected World
- » What is Graph Analytics?
- » Graphs in Machine Learning
- » Social and Information Network Analysis
- » Structural Analysis and Visualization of Networks
- » Latent Space Model for Road Networks to Predict Time-Varying Traffic
- » Three Applications of Deep Learning in Big Data Analytics
- » Fog Computing vs. Edge Computing
- » From Big to Now - The Changing Face of Data
- » Fast Data at Internet Scale with Amazon ElastiCache for Redis
- » Fast Data, Fast Monitoring
- » Wide & Deep Learning; Memorization + Generalization with TensorFlow
- » Keynote - TensorFlow Dev Summit 2017
- » Cloud of Things Overview
- » Big Data and Smart Data
- » Gunrock
- » 5 Ways to Make Your Hive Queries Run Faster
- » TensorFlow Introduction
- » Apache Ignite In-Memory Data Fabric
- » Introduction to HDFS Erasure Coding in Apache Hadoop
- » Min-cost Flow Network Algorithms
- » Elasticity with YARN
- » Knowledge Curation and Knowledge Fusion
- » Self-Curating Databases
- » Lightning Fast Social Media Analytics
- » Statistics-Driven OLAP Acceleration using Query Column Sets
- » Apache Calcite Overview
- » A Better B-Tree in Hekaton
- » The Bw-Tree; A B-tree for New Hardware
- » Hekaton Research
- » Distributed Transactions
- » ACID Isolation Level
- » Notes About Memory Allocation Redesign
- » Postgres Modifications
- » The Databaseology Lectures
- » C++ Arena Allocation Guide
- » Region-based Memory Management
- » Zeppelin Tajo Interpreter
- » What is VoltDB?
- » Release Notes - Tajo - Version 0.11.1
- » Peloton Architecture
- » Insert-Only Implementation Strategies
- » Understanding the SQL Server Columnstore Index
- » Hekaton Breaks Through
- » Compensating Transaction
- » In-Memory Column Store Architecture Overview
- » Advantages & Disadvantages of an In-Memory Database
- » Main Memory DBMS
- » HYBRID WORKLOADS AND HTAP
- » Peloton
- » MVCC Overview
- » SAP HANA
- » HYRISE
- » Main Compensation and Delta Compensation
- » Aggregate Cache
- » MonetDB Source compilation on OS X
- » SDN and Big Data
- » Connected Components in MapReduce and Beyond
- » Connected Components in MapReduce and Beyond
- » Analytics in Motion (AIM)
- » Big Data is (at least) Four Different Problems
- » Real-time Big Data Analytics
- » Queries on Compressed RDDs
- » HiBench Suite
- » MultiQx-GPU
- » Concurrent Analytical Query Processing with GPUs
- » Where are the GPU based SQL databases?
- » Comparing Relational Databases, Memory Cache, and NoSQL
- » Oracle In-Memory Database Cache Overview
- » MapGraph
- » Central Office Re-architected as a Datacenter (CORD)
- » Introducing TPCx-HS Benchmark for Big Data
- » Building LuxRender on OS X
- » Machine Driven, Human Guided Data Curation for Decision Advantage and Action
- » Twitter Analysis with Apache Spark and IBM Watson
- » Rethinking SQL for Big Data with Apache Drill
- » Organizational Charts
- » The Pushdown of Everything
- » Machine Learning as the Key to Personalized Curation
- » Big Data, Fast Data The Need for In Memory Database Technology
- » Arrary DBMS
- » Arrary Databases
- » Michael Stonebraker's Talk
- » Michael Stonebraker's Talk
- » Running Hadoop MapReduce on Tachyon
- » What is HTAP?
- » A Taste of Random Decision Forests on Apache Spark
- » ADAM Project
- » Spark - The Ultimate Scala Collections
- » BDAS Software Stack
- » Basic ONOS Tutorial
- » Spark Cluster Configuration
- » Sample Data
- » Building Tachyon Master Branch
- » Creating Applications using Spark Streaming
- » Creating a Spark Applications
- » Working with RDD Operations
- » RAMCloud Presentations
- » Teaching creative computer science
- » BlinkDB Review
- » RAMCloud Training
- » Kudu - New Apache Hadoop Storage for Fast Analytics on Fast Data
- » GridGain In-Memory Data Fabric
- » Discardable Memory and Materialized Queries
- » 2014 ACM A.M. Turing Lecture
- » What is the Future of Hadoop?
- » What is the Future of Hadoop?
- » Sparrow Paper Review
- » Spark Architecture Shuffle
- » Explore In-Memory Data Store Tachyon
- » Tachyon Overview
- » Perform SQL Selects on R Data Frames
- » R Graphics
- » Google's R Style Guide
- » Approximate Aggregation Queries in Presto
- » Off-heap Memory in Apache Flink and the curious JIT compiler
- » AMP Camp 6
- » Spark 1.5 DataFrame API Highlights
- » Fundamentals of Parallel Computing with the GPU
- » Text Mining and Knowledge Graphs in the Cloud
- » Knowledge Graph and Cognitive Computing
- » Using Presto to combine data from Hive and MySQL
- » IBM Watson at Work
- » Using HyPer with PostgreSQL Drivers
- » Knowledge Graph
- » Big Data and Machine Learning - Keys to AI Progress
- » Project Tungsten
- » Building Good Docker Images
- » SparkR Setting for RStudio
- » SparkR
- » Cognitive Computing
- » Spark Lab 3
- » Spark Lab 2
- » Diving into Spark Streaming's Execution Model
- » Using Electronic Health Records for Better Care
- » 6 Big Data Analytics Use Cases for Healthcare IT
- » Four Use Cases for Healthcare Predictive Analytics, Big Data
- » Five open source Big Data projects to watch
- » Reservoir Sampling in MapReduce
- » Clinical Data Repository Versus a Data Warehouse
- » Top 50 Data Science Resources
- » High-throughput, low-latency, and exactly-once stream processing with Apache Flink
- » Hyper
- » From Big Data to Fast Data
- » SAP Hana In-Memory Explained In Nine Minutes
- » Business unIntelligence
- » The Challenges of Data Science
- » How Data Science Driven Software is Eating the Connected World
- » Data Curation as Publishing for the Digital Humanities
- » How WellCare Accelerated Big Data Delivery to Improve Analytics
- » Sharing Experiences in Cloud Adoption
- » IBM Hybrid Transaction Analytic Processing HTAP
- » What is Hybrid Transaction/Analytical Processing (HTAP)?
- » CIOs and the Ongoing Data Persistence Struggle
- » Eight Big Trends in Big Data Analytics
- » Hybrid Trasansaction/Analytical Processing (HTAP)
- » Hybrid Trasansactional/Analytical Processing (HTAP)
- » HTAP and The Future of Data
- » Does ethical content curation exist? A data-driven answer
- » Stonebraker points to data curation as next integration step
- » Three Approaches to Scalable Data Curation
- » The Landscape of Big Data, Curation
- » Data Curation
- » Tackling Data Curation
- » Potential Novel Applications of Open SDN
- » Hybrid Unified Communications and Collaboration
- » Hype Cycle
- » SDN Note
- » RAMCloud Overview
- » RAMCloud
- » Open Network Operating System
- » The Virginian Database
- » The Analytical Bootstrap
- » DAQ Introduction
- » A New Paradigm for Approximate Query Processing
- » Understanding the Differences between SDN and Server Virtualization
- » Future of big data analytics
- » Five most popular similarity measures implementation in python
- » Massive Throughput Database Queries with LLVM on GPUs
- » Open Daylight Technical Overview
- » Hadoop + GPU Architecture
- » Overview of the Apache Flink
- » Apache Flink Seminar
- » Lambda Architecture
- » Apache MRQL Installation Instructions
- » Common Misconceptions about SQL on Hadoop
- » Apache MRQL
- » MapD (Massively Parallel Database) Overview
- » Data Science using GPUs
- » Apache Drill Introduction
- » IBM Juices Hadoop With Java On Tesla GPUs
- » Broadcast Join in Tajo
- » Tajo Cluster Architecture
- » Apache Hadoop vs. IBM Platform Symphony and Infosphere BigInsights
- » How HPC is Hacking Hadoop
- » High-Performance Computing Cluster
- » Zeppelin Tutorial
- » Teradata Bets Big on Presto for Hadoop SQL
- » Introduction to Data Science with Apache Spark
- » The Internet of Things Transforms Transactions with Apache Spark
- » Improving Spark for Data Pipelines with Native YARN Integration
- » BlinkDB User Guide
- » Totally Lazy
- » A SQL Query Compiler
- » Recent performance improvements in Apache Spark
- » Bringing Spark Closer to Bare Metal
- » Best SQL-on-hadoop Tool
- » Data Exploration Using BlinkDB
- » Programming With SampleClean
- » SampleClean
- » Running BlinkDB Locally
- » Large Graph-Mining - Power Tools and a Practitioner's Guide
- » Hadoop-RDMA
- » Apache Spark - Caching and Checkpointing Under the Hood
- » Tensor Decomposition
- » Higher-order Singular Value Decomposition
- » Smoothed Analysis of Tensor Decompositions
- » Spark for Unconventional Cores
- » Aparapi for Unconventional Cores
- » Apache Phoenix
- » Immutability
- » Parallelism
- » Column Orientation
- » Composing and Scaling Data Platforms
- » Elements of Scale
- » What is Mesos?
- » Data Governance Initiative
- » FAQ for the REEF
- » Introduction to BlinkDB
- » Introduction to REEF
- » Spark with Python Notebook on Mac
- » MapReduce for C - Run Native Code in Hadoop
- » Spark Notebook
- » Spark-GPU Cluster Development in a Notebook
- » 5 Ways to Make Your Hive Queries Run Faster
- » 39 Data Visualization Tools for Big Data
- » HIVE 0.14 Cost Based Optimizer (CBO) Technical Overview
- » Deep Dive into Spark SQL’s Catalyst Optimizer
- » Introducing DataFrames in Spark for Large Scale Data Science
- » Twitter Scalding
- » Apache Zeppelin
- » Transaction Processing on Confidential Data using Cipherbase
- » Introduction to the Spark
- » Big Spatial Data Processing using Spark
- » SpatialSpark
- » New Directions for Spark in 2015
- » The Spark SQL Optimizer and External Data Sources API
- » DataFrame and SQL Operations
- » Design Patterns for using foreachRDD
- » Output Operations on DStreams
- » Transformations on DStreams
- » DStream Sources
- » Discretized Streams
- » Spark Streaming Basic Concepts
- » Spark Streaming Quick Example
- » Spark Streaming Overview
- » Useful Research Related to Apache Drill
- » Apache Spark
- » An Introduction To Software Defined Networking
- » 10 ways to query Hadoop with SQL
- » Application Interaction with the ResourceManager
- » Resource Manager
- » Build YARN Apps on Hadoop with Apache Slider
- » Analytic Processing Environment (APE)
- » Analytics vs. OLTP
- » Layers of Query Processing
- » Database Workloads
- » Workload Types
- » Detailed Characteristics of an Analytic Workload
- » Characteristics of an Analytic Workload
- » Workload Management for Big Data Analytics
- » SDN과 NFV와 네트워크 가상화의 차이점 이해하기
- » Apache Hadoop YARN Architecture
- » DryadLINQ
- » Dryad
- » Join Optimization
- » Map-Side Join Vs. Join
- » What is map side join and reduce side join?
- » Hive Architecture
- » Translate from MapReduce to Apache Spark
- » An Insight into Hadoop YARN NodeManager
- » Hadoop-GIS Spatial Queries
- » Running a cluster of virtual machines with Hadoop
- » SIX sparkling features of Apache Spark!
- » Use Parquet with Impala, Hive, Pig, and MapReduce
- » Use Parquet with Impala, Hive, Pig, and MapReduce
- » Actian Unleashes SQL Users on Hadoop with Easy Access, Faster Performance
- » Actian Unleashes SQL Users on Hadoop with Easy Access, Faster Performance
- » Presto as a Service
- » Presto as a Service
- » HIVE as a Service
- » HIVE as a Service
- » Understanding the world of SQL on Hadoop.
- » How to Develop Hadoop Tests
- » MRUnit Tutorial
- » Serialization
- » HIVE TPC-DS Benchmark
- » HIVE TPC-DS Benchmark
- » Distributed Computing with Spark
- » Distributed Computing with Spark
- » Why Oracle Big Data SQL Potentially Solves a Big Issue with Hadoop Security
- » Why Oracle Big Data SQL Potentially Solves a Big Issue with Hadoop Security
- » Apache Tez Presentation
- » Announcing Apache Pig 0.13.0
- » Benchmarking Apache Hive 13 for Enterprise Hadoop
- » In-Stream Big Data Processing
- » In-Stream Big Data Processing
- » Apache Hadoop YARN ResourceManager
- » Apache Hadoop YARN ResourceManager
- » Introduction To Pivotal's Next Generation Analytic Data Lake
- » Introduction To Pivotal's Next Generation Analytic Data Lake
- » War of the Hadoop SQL engines. And the winner is …?
- » War of the Hadoop SQL engines. And the winner is …?
- » Exploring Pivotal HD Single Node (VM)
- » Exploring Pivotal HD Single Node (VM)
- » How Pivotal Works
- » How Pivotal Works
- » Parquet - Columnar Storage for the People
- » Parquet - Columnar Storage for the People
- » Pivotal Big Data Suite
- » Pivotal Big Data Suite
- » Pivotal HD Introduction & Demo
- » Pivotal HD Introduction & Demo
- » Special "Use Cases" Big Data & Brews - Hortonworks, Pivotal, MapR
- » Special "Use Cases" Big Data & Brews - Hortonworks, Pivotal, MapR
- » What is Apache Drill?
- » What is Apache Drill?
- » Drilling into Big Data with Apache Drill
- » Drilling into Big Data with Apache Drill
- » Fun with TPC-H (Part 1)
- » Fun with TPC-H (Part 1)
- » Implementing Drill Math Functions
- » Implementing Drill Math Functions
- » Presto By Facebook – A SQL Engine
- » Presto By Facebook – A SQL Engine
- » Big Data - The Hadoop Data Warehouse
- » Big Data - The Hadoop Data Warehouse
- » Building a Data Warehouse with Hadoop
- » Building a Data Warehouse with Hadoop
- » Why does MapReduce + GPU Computing?
- » Why NoSQL?
- » Apache Spark Documentation
- » Google Cloud Dataflow, a Cloud-native data processing service
- » Datawarehouse
- » Selecting the right SQL-on-Hadoop engine to access big data
- » Big Data Benchmark
- » Apache Spark
- » Optiq
- » Adding Acid Transactions in Hive
- » Yarn The Key to Overcoming the Challenges of Broad based Hadoop Adoption
- » Challenges of Implementing an Advanced SQL Engine on Hadoop
- » SparkR Enabling Interactive Data Science at Scale on Hadoop
- » Hbase Read High Availability Using Eventually Consistent Region Replicas
- » How Hadoop and Hive Change the Data Warehousing Game Forever
- » Big Data Management System Smart SQL Processing
- » Query Optimization Techniques and JIT based Vectorized Engine
- » Pig on Tez - Low Latency ETL with Big Data
- » Cost Based Query Optimization in Hive
- » Low Latency SQL on Hadoop
- » Building a Unified Data Pipeline in Apache Spark
- » Big Data Architecture
- » Comparing Information Architecture Operational Paradigms
- » Big Data Architecture Capabilities
- » How to prepare for SDN
- » What is SQL-on-Hadoop?
- » Apache Storm Basics
- » What does “100 times faster than Hive” actually mean?
- » GraphX Programming Guide
- » TPC Benchmark
- » M7 - Native Storage for MapR Tables
- » M7 - Native Storage for MapR Tables
- » Hadoop 2.4.0 Installation on Mac OS X Mavericks
- » Software-Defined Networks
- » Future of the Network Documentary
- » A Leap Forward With SQL on Hadoop
- » Special "How it Works" Big Data & Brews
- » GPU Programming for the Data Sciences
- » 10 undeniable reasons people hate Big Data
- » Hadoop Sector will Have Annual Growth of 58% for 2013-2020
- » Why Impala Continues to Lead?
- » Apache Spark Resource Management and YARN App Models
- » Google Spanner
- » Column-Family Stores
- » Key-Value and Document Data Models
- » Development Tools for Big Data
- » Apache Tajo JDBC Driver
- » Apache Tajo HCatalog Integration
- » Spark for Data Science; A Case Study
- » Apache Tajo Backup and Restore
- » Apache Tajo Table Partitioning
- » An Insight into Hadoop Yarn Resource Manager
- » Apache Tajo SequenceFile
- » 5 technologies that will help big data cross the chasm
- » Apache Tajo Parquet
- » How Apache Hadoop YARN HA Works
- » Apache Tajo RCFile
- » Apache Tajo Table Management
- » Apache Tajo CSV (TextFile)
- » Papers to Read
- » Apache Tajo Functions
- » Apache Tajo SQL Language
- » Apache Tajo Shell
- » Apache Tajo™ 0.8.0 Configuration
- » Apache Tajo™ 0.8.0 Released!
- » Apache Tajo™ 0.8.0 Documentation
- » The Stinger Initiative From HortonWorks With Hadoop
- » Bigtable
- » Chubby
- » Big Data & Brews - Ari Zilka, CTO of Hortonworks' Talk
- » The Google File System (GFS)
- » Stinger Intiative - Making Apache Hive 100 Times Faster
- » Stinger - Interactive Query for Hive
- » Overview of Data Storage and Coordination Services
- » Simple YARN Application
- » Underlying Communication Paradigms
- » Overall Architecture and Design Philosophy
- » Comparing Apache Tez and Microsoft Dryad
- » Apache Spark and Apache Tez
- » Introducing the case study - Google
- » Integration Tajo with Hive
- » Choosing the Right SQL-on-Hadoop
- » How to Run a Simple Apache Spark App in CDH 5
- » NewSQL Vs. SQL on Hadoop
- » Presto as a Service
- » Presto as a Service
- » Apache Hadoop YARN – Related Work
- » Adding ACID to Apache Hive
- » Adding ACID to Apache Hive
- » Eight SQL on Hadoop Challenges
- » 11 SQL-on-Hadoop Tools
- » Healthcare Does Hadoop
- » Processing streaming data in Hadoop with Apache Storm
- » Interactive Query for Hadoop with Apache Hive on Apache Tez
- » Introducing Apache Tez 0.4
- » Big Data Genomics Sequencing
- » Failures in YARN
- » Failures in Classic MapReduce
- » YARN Framework and Fault Tolerance
- » Smart Things vs. Many Experienced Things
- » Apache Hadoop YARN – Node Manager (NM)
- » Hardening Hadoop for Healthcare with Project Rhino
- » Hardening Hadoop for Healthcare with Project Rhino
- » Apache Tajo
- » Build Instructions for Apache Tajo
- » Apache Hadoop YARN – Application Master (AM)
- » Apache Hadoop in 2013 - The State of the Platform
- » Apache Hadoop YARN – Architecture Overview
- » Apache Hadoop YARN – Resource Manager (RM)
- » Apache Hadoop YARN – History and Rationale, Shared Clusters
- » Functional Programming
- » Navier-Stokes Equations
- » Implementing Graph-Based Applications
- » Designing Graph-Based Applications
- » Data-intensive Computing
- » Network Topology and Hadoop
- » Ensuring the Validity, Veracity, and Volatility of Big Data
- » Operationalizing Big Data
- » Modern Oil & Gas Architectures Built with Hadoop
- » Modern Oil & Gas Architectures Built with Hadoop
- » Using Avro in MapReduce Jobs with Pig
- » Using Avro in MapReduce Jobs with Java
- » Using Avro in MapReduce Jobs with Hive
- » Using Avro in MapReduce Jobs with Hadoop Streaming
- » NoSQL Databases
- » Visualization for Data-Intensive Science
- » Theory of Everything
- » Stanford Network Analysis Platform(SNAP)
- » Gray’s Laws Database-centric Computing in Science
- » Connecting to the Scientists
- » Big Data Dilemma
- » Polyglot Persistence
- » Community Detection - Clustering Coefficient
- » Hive on Tez
- » Functional Requirements of Hive on Tez Phase I
- » Query Planning of Hive on Tez
- » Design of Hive on Tez
- » Apache Tez 0.3 Released!
- » Predictive Methodologies - Analysis of Time and Space
- » Predictive Methodologies - Analysis of Space
- » Predictive Methodologies - Analysis of Social Networks
- » Theoretical Foundations of Data Mining and Predictive Analytics
- » Data Used in Predictive Policing
- » Operational Challenges of Predictive Policing
- » Forecast Vs. Prediction
- » Recommendations
- » Predictive Policing Myths and Pitfalls
- » Prediction-Led Policing Process and Prevention Methods
- » Facebook Presto
- » Apache Drill
- » Predictive Policing
- » A Taxonomy of Predictive Methods
- » Apache Hadoop YARN – History and Rationale
- » “Big Data” Promises a Revolution
- » As MapReduce fades, Apache Spark is now a top-level project
- » Apache Hadoop YARN – ResourceManager
- » Apache Hadoop YARN – Yet Another Resource Negotiator
- » Apache Hadoop YARN – NodeManager
- » Apache Hadoop YARN – Concepts and Applications
- » Apache Hadoop YARN – Background and Overview
- » Introducing Apache Hadoop YARN
- » T-Shaped Data Scientists
- » Adapting to Change
- » Agile Big Data
- » Scales of Big Data
- » The Variety of Data Scientists
- » The Real-Time Big Data Architecture (RTDBA) Stack
- » The Five Phases of Real Time
- » Case Studies of Analyzing Data
- » Data Science, Engineering, and Data-Driven Decision Making
- » Clustering Data Scientists
- » PredictionIO
- » Key Points from NoSQL Distilled
- » Multi-tenant Database Systems
- » Big Data in Motion
- » Tez Design - Introduction
- » Building a Hybrid Modern Data Architecture for Apache Hadoop
- » Continuous Quries Languages
- » Semantics of Relations in Continuous Queries
- » Continuous Quries as Views
- » Building the Health Information Infrastructure for the Modern ePatient
- » Solving the Wanamaker Problem for Healthcare
- » Continuous Query Semantics and Operators (Part II)
- » Stream Windows
- » Continuous Query Semantics and Operators (Part I)
- » Parallel R
- » Writing Input And Output Adapters
- » Stream Models
- » Understanding the Types of Big Data Problems
- » Understanding Human Dynamics
- » Esper Relational Database Adapter
- » Event Rendering to XML and JSON
- » Esper Socket Adapter
- » Esper Adapter Concept
- » Writing a Tez Input, Processor and Output
- » Runtime API in Apache Tez
- » Re-Using Containers in Apache Tez
- » Introducing Tez Sessions
- » Data Processing API in Apache Tez
- » Apache Tez Dynamic Graph Reconfiguration
- » Apache Tez A New Chapter in Hadoop Data Processing
- » Introduction to the Tez
- » Principal Component Analysis
- » Data Stream Management
- » Physical Properties and selection of thermodynamic models
- » Centrifugal Compressor Efficiency - Part 4
- » Centrifugal Compressor Efficiency - Part 3
- » Centrifugal Compressor Efficiency - Part 2
- » Centrifugal Compressor Efficiency - Part 1
- » In-Memory Caches
- » Pattern Matching Techniques
- » Monte-Carlo Methods An Introduction
- » PRODML Data Schema and API Specifications
- » The Invention of Stream Computing
- » Real-time Operational Intelligence
- » Explaining Agile
- » Introduction to Esper for Java
- » The Emergence of NoSQL
- » Real-Time Data Stream Manager (RTDSM) Interface Specification
- » Modelling in Big Data
- » Analyzing Data in Motion A Real-World View
- » Understanding trade-offs with Brewer’s CAP theorem
- » Applications using graph representation
- » YARN (MapReduce 2)
- » Stream Data Schema Design
- » Introduction to Stream Computing
- » Streams Application Design
- » Analytics vs. Predictive Analytics
- » Streams design patterns
- » The evolution of analytics
- » Extreme Programming
- » Thermodynamics Basic Concepts
- » Scrum Agile Development Process
- » Impedance Mismatch
- » The Value of Relational Databases
- » What is NoSQL?
- » Neo4j
- » Graph Databases
- » NoSQL History
bioinformatics
- » A Multi-Agent System for Automating Scientific Discovery
- » Neuro-Symbolic Scientific World Models in Drug Discovery
- » Multimodal Multi-Agent AI Co-Scientists for Drug Discovery
- » Epistemic Hyper-Relational Knowledge Graphs for AI Co-Scientists
- » Biomedical Literature Vector DB for Agentic RAG
- » AI-based discovery of new therapeutic modal drug candidates
- » Protein Structure Prediction and the Paradigm Shift in Modern Science
- » Recent Structural Tokenization Research Trends
- » Flow Matching-Based Protein Generation Technology
- » Diffusion-Based Adaptive Tokenization Analysis
- » Protein Structure Tokenization
- » Drug-Discovery-Specific LLMs
- » LLM Covering the Entire Drug Development Cycle
- » AlphaFold 3 & Agentic Drug Discovery
- » Autonomous Agentic AI in Drug Discovery
- » AlphaFold 3 & LLM Agents
- » Next-Gen Drug Design: AlphaFold 3 & IsoDDE Fusion
- » Drug Discovery LLM: In-depth Analysis Report
- » AI Innovation for Exploring Unexplored Biological Systems
- » Sequence-Structure Design and Optimization of Unnatural Enzymes
- » LLM In-Context Learning & Hyper-Relational Knowledge Graphs
- » Drug Development Innovation: TxGemma and Hyper-Relational KG
- » Biomedical Knowledge Graphs with Multi-Modal Graph Construction
- » Biomedical Knowledge Graphs (BKGs) and Agentic AI
- » Bio-Artificial Intelligence & Graph Neural Networks
- » Drug Development Using LLM-based Biomedical Knowledge Graphs
- » LLM-Based Biomedical Knowledge Graph Mining
computer graphics
- » AlphaFold 3 & Computer Graphics Convergence Study
- » NVIDIA Keynote at SIGGRAPH 2023
- » Hybrid Grains
- » Beautiful Layered Materials, Instantly
- » Gaussian Material Synthesis
- » Self-Illuminating Explosions
- » An Efficient Scattering Material Representation
- » Leveraging Activation Sparsity for Training Deep Neural Networks
- » Deep Photo Style Transfer
- » AI Creates 3D Models From Faces
- » A modular GPU raytracer using OpenCL for non-interactive graphics
- » Semantic Scene Completion from a Single Depth Image
- » Real-Time Oil Painting on Mobile Hardware
- » Geometric Detail Transfer
- » Space-Time Video Completion
- » AI Makes Stunning Photos From Your Drawings
- » Real-time Fiber-level Cloth Rendering
- » Shape and Material from Video
- » Learning to Fill Holes in Images
- » Calendar of Computer Graphics Events
- » AI Builds 3D Models From Images With a Twist
- » How Do Hollywood Movies Render Smoke?
- » Fast Photorealistic Fur and Hair With Cone Tracing
- » Enhance Super Resolution From Google
- » Large-Scale Fluid Simulations On Your Graphics Card
- » AI Makes 3D Models From Photos
- » Text Style Transfer
- » Amazing Slow Motion Videos With Optical Flow
- » Neural Network Learns The Physics of Fluids and Smoke
- » Stunning Video Game Graphics With Voxel Cone Tracing
- » Papers that have used pbrt
- » Mathematical Methods for Robotics, Vision, and Graphics
- » Image Synthesis From Text With Deep Learning
- » PBRT Installation on macOS
- » Water Wave Simulation with Dispersion Kernels
- » Crumpling Sound Synthesis
- » Introduction to "Physically Based Shading in Theory and Practice"
- » Multiphase Fluid Simulations
- » Sound Propagation With Bidirectional Path Tracing
- » 3D Printing Acoustic Filters
- » SIGGRAPH 2016 Papers on the Web
- » Modeling Colliding and Merging Fluids
- » Surface-Only Liquids
- » Artistic Style Transfer For Videos
- » SIGGRAPH 2016 – Technical Papers Trailer
- » Separable Subsurface Scattering
- » Real-Time Shading With Area Light Sources
- » Face2Face; Real-Time Facial Reenactment
- » Embree; High Performance Ray Tracing Kernels
- » Narrow Band Liquid Simulations
- » Photos @ EDBT 2016
- » 3D Depth From a Single Photograph
- » Research Papers in Computer Graphics
- » Readings in Physically Based Rendering
- » Metropolis Light Transport
- » Data Visualization
- » SIGGRAPH 2015 papers on the web
- » SIGGRAPH 2015 - Technical Papers Trailer
- » 39 Data Visualization Tools for Big Data
- » Keep Your Crises Small
- » Creativity, Inc. Interview
- » SIGGRAPH 2014 Technical Papers
- » SIGGRAPH 2014 Papers
- » Physically Based Shading in Theory and Practice
- » The Forgotten History Of CGI
- » Visualization for Data-Intensive Science
- » A Material Point Method For Snow Simulation
- » Reflections on Image-Based Modeling and Rendering
- » Korean Computer Graphics Conference 2013
data management
- » VLDB 2026: From Text-to-SQL to Provenance-Aware Workflows
- » From LLM-Enabled Databases to Agent-Native Data Systems
- » Agentic Data Systems: From LLM Applications to Database-Native Agents
- » A Unified Schema Matching Framework with Large Language Models
- » Dynamic Integration of Multimodal Entity Linking with LLM
- » Structure-Guided Evidence Packing for LLM Schema Matching
- » Enhancing Multimodal Entity Linking with Fine-Grained Attributes
- » SIGMOD 2026: From Relational Databases to AI-Native Data Systems
- » Conclusion: DuckDB
- » Performance considerations for large datasets
- » Building and deploying data apps
- » Using DuckDB in the Cloud with MotherDuck
- » Building data pipelines with DuckDB
- » Accessing Remote Data Using DuckDB
- » DuckDB in the cloud with MotherDuck
- » Using DuckDB with JupySQL
- » Integrating with the Python ecosystem
- » Using DuckDB with JSON Files
- » Exploring data without persistence
- » Performing EDA with DuckDB
- » Using DuckDB with Polars
- » Executing SQL queries
- » A Primer on SQL
- » Advanced aggregation and analysis of data
- » Getting Started with DuckDB
- » Importing Data into DuckDB
- » Getting Started with DuckDB
- » Benchmarking for Single-Cell Time Series Forecasting
- » The Paradox of Data Filtering: Transformation from Junk Data
- » Awesome Vector Database
- » How to Write a Great Research Paper
- » Vision Transformer - Keras Code Examples
- » Vision Transformer
- » MLP-Mixer; An all-MLP Architecture for Vision
- » From AlphaGo to MuZero
- » Moral Machines; How culture changes values?
- » Generative Adversarial Networks
- » Hardness of Approximation Between P and NP
- » GPT-3 = Generation Pre-trained Transformer 3
- » Graph Attention Networks Implementation
- » Introduction to Pytorch Geometric
- » Deep Learning for Graphs
- » Geometric Deep Learning
- » Graph Neural Networks - Models and Applications
- » Matching of Matching Graphs
- » Graph Classification using Structural Attention
- » Approximate Personalized PageRank on Dynamic Graphs
- » GCNs for Web-Scale Recommender Systems
- » Inductive Representation Learning on Large Graphs
- » Write Research Paper Outline
- » How to Respond to Reviewer Comments
- » Limitations of Graph Neural Networks
- » Choice of Graph Representation
- » Inductive Representation Learning on Temporal Graphs
- » Applications of Graph ML
- » Machine Learning with Graphs
- » How to Review a Research Paper
- » Approximate standing queries on Stream Processing
- » Learning Mesh-Based Simulation with Graph Networks
- » Temporal Graph Networks for Deep Learning on Dynamic Graphs
- » Graph Neural Networks and Knowledge Graph Completion
- » Parallel and Distributed Computing in Python with Dask
- » Reducing Communication in Graph Neural Network Training
- » Mathematical Foundations of the GraphBLAS and Big Data
- » Graph Signal Processing - Accounting for Geometry in Data
- » Graph Signal Processing for Machine Learning Applications
- » Papers on Recommendation Systems
- » Representational Power of Graph Neural Networks
- » Tunable Stream Graph Embeddings at Scale
- » Graph Neural Networks
- » Graph Convolutional Networks using only NumPy
- » Temporal Graph Networks for Dynamic Graphs
- » Graph Algorithms as Matrix Vector Products
- » Distributed Machine Learning with Python
- » Deep Networks Are Kernel Machines
- » How the Quest for the Ultimate Learning Machine Will Remake Our World
- » Fast Distributed Algorithms for Girth, Cycles and Small Subgraphs
- » Graph Sketching, Streaming, and Sampling
- » Theoretical Foundations of Graph Neural Networks
- » Efficiently Answering Span Reachability Queries
- » Probabilistic Reachability for MDPs
- » How computer science can help fight COVID-19
- » Enable Digital Transformation with Big Spatial Data & Analytics
- » Online Approximation Techniques for Spatial Data
- » Sparse Matrices Beyond Solvers
- » New Machine Learning Tool Tracks Urban Traffic Congestion
- » Graph Convolutional Neural Networks for Molecule Generation
- » Deep Learning on Graphs
- » Principles and Applications of Relational Inductive Biases
- » Traffic Prediction with Advanced Graph Neural Networks
- » Papers on Graph Neural Networks
- » Self-Driving Databases
- » Non-Volatile Memory for Database Management Systems
- » Using Apache Arrow, Calcite and Parquet to build a Relational Cache
- » Data Vocalization
- » Cloud of Things Overview
- » Blockchain Explained
- » Proceedings of the VLDB Endowment
- » Data Preparation for Machine Learning
- » How to Prepare Data For Machine Learning
- » IoT, Azure, Machine Learning and more
- » IBM Watson IoT Platform
- » Revisiting Reuse in Main Memory Database Systems
- » What's New with NewSQL?
- » Spark-GPU; An Accelerated In-Memory Data Processing Engine on Clusters
- » GPU SQL Query Accelerator
- » Multi-core Parallelism in a Column-store
- » Self-Driving Database Management Systems
- » Graph Mining for Log Data
- » Understanding Multitenancy and the Architecture of the Salesforce Platform
- » Probabilistic Ranking Problem
- » Data Blocks; Hybrid OLTP and OLAP on Compressed Storage using both Vectorization and Compilation
- » PVLDB Papers
- » Progressive skyline computation in database systems
- » Proceedings of the VLDB Endowment, Volume 10
- » Vectorized Executor
- » Skyline Operator
- » Top 10 Strategic Technology Trends 2016
- » Faster In Memory Computing with No Deadlocks
- » The Emergence of Converged Data Platforms and the Role of In Memory Computing
- » Parallel Data Processing
- » Apache Ignite In-Memory Data Fabric
- » Smart Data Discovery
- » Introduction to LLVM
- » Breakthrough Processor and System Design with SPARC M7
- » Life Beyond Column-Stores - Exploiting intra-cycle parallelism
- » OLTPBench
- » CrowdSky; Skyline Computation with Crowdsourcing
- » Efficient Computation of Containment and Complementarity in RDF Data Cubess
- » Data Processing in Modern Hardware
- » Verification of Evolving Graph-structured Data under Expressive Path Constraints
- » Top-k Indexes Made Small and Sweet
- » Dynamic Graph Queries
- » Worst-Case Optimal Algorithms for Parallel Query Processing
- » Declarative Probabilistic Programming with Datalog
- » Concurrency Control and Recovery for Search Trees
- » How DeepMind Conquered Go With Deep Learning
- » 자유가 없는 나라의 공부
- » Skip List
- » Transactional Memory in Practice
- » DB2 for z/OS Best Practice; Locks and Latches
- » Database Recovery - Basic Concepts
- » Latches
- » PostgreSQL
- » Vagrant Tutorial
- » Introduction to Vagrant
- » A Hands-free Adaptive Store
- » The Bw-Tree Key-Value Store
- » Bitmap Indices
- » IBM Cognos Analytics
- » Main Memory Databases
- » Dictionary-based Order-preserving String Compression
- » The Merits of Data Compression
- » DBMS Components
- » Latches, Spinlocks, and Lock Free Data Structures
- » Database Systems Course
- » Gartner Top 10 Tech Trends for 2016
- » CES 2016 Keynote
- » In-Memory Accelerator for Hadoop
- » Building Postgresql on OS X
- » TPC-H
- » Setting Up An Organized Folder Structure
- » TPC-DS
- » In-Memory Data Management Course
- » Databaseology Lectures
- » Zeppelin Deployment
- » Zeppelin Structure
- » Zeppelin Installation
- » MySQL Installation on Ubuntu
- » PVLDB 2015 Vol. 9
- » Data Engineering Course
- » Apache Spark vs. MapReduce
- » Korean Constitution
- » Database Reading List
- » Big Data, Fast Data The Need for In Memory Database Technology
- » Arrary DBMS
- » Arrary Databases
- » Introduction to LLVM
- » MySQL Installation on Mac OS X
- » Sample Data
- » RAMCloud Presentations
- » Teaching creative computer science
- » Discardable Memory and Materialized Queries
- » 2014 ACM A.M. Turing Lecture
- » Optimizing Big Data Through Curation
- » Cognitive Computing
- » SAP S4 HANA Technical White Board
- » The Challenges of Data Science
- » How Data Science Driven Software is Eating the Connected World
- » How WellCare Accelerated Big Data Delivery to Improve Analytics
- » What is Hybrid Transaction/Analytical Processing (HTAP)?
- » Eight Big Trends in Big Data Analytics
- » My Top 10 Assertions about Data Warehouses
- » Apache Tajo Internal
- » Readings in Data Management
- » Database Management Systems
- » Planning the Approach
- » Database Management Systems
- » Readings in Database Systems
- » Query Optimization Bibliography
- » PostgreSQL
- » Advantages and Drawbacks of Using Stored Procedures for Processing Data
- » What is SQL-on-Hadoop?
- » What does “100 times faster than Hive” actually mean?
- » GraphX Programming Guide
- » TPC Benchmark
- » Hadoop 2.4.0 Installation on Mac OS X Mavericks
- » Choosing distribution models
- » Hadoop Sector will Have Annual Growth of 58% for 2013-2020
- » Why Impala Continues to Lead?
- » Measures of Query Cost
- » Query Processing
- » Query Transformation
- » Database Conferences
- » Query Optimizer
- » Research Topics in Database Systems
- » ACID Properties of Transactions
- » Introduction to Distributed Database Management Systems
- » Introduction to Data Warehousing
- » Date's Twelve Rules for a DDBMS
- » Depth of Knowledge
- » Mapping and Folding and the Map-Reduce Paradigm
- » Codd's 12 Rules
- » OLAP vs. OLTP
- » Comparison - Ad-hoc vs Stored Procedure vs Dynamic SQL
- » FINDING INFORMATION ON THE WEB
- » Advanced Metasearch Engine Technology
- » Multi-tenant Database Systems
- » Building a Hybrid Modern Data Architecture for Apache Hadoop
- » Building the Health Information Infrastructure for the Modern ePatient
- » Modelling in Big Data
- » VLDB 2013
design patterns
- » Notes on Graph Theory
- » Visual Studio Code, CMake and LLDB
- » Extreme Team
- » Visual Studio Code - C++ Development
- » UML Tools for Python
- » Introduction to gRPC
- » Design Patterns in Python
- » Sequential Implementation of Mesoscopic Simulation
- » Limitations of Macroscopic and Mesoscopic Simulation
- » Simulation Loop
- » Mesoscopic Simulation
- » Traffic Prediction
- » Apache Mesos
- » Distributed Systems
- » High-Performance Mesoscopic Traffic Simulation
- » Microscopic Simulation
- » Macroscopic Simulation
- » Traffic Simulation Background
- » T tree
- » Cellular Automata
- » Pair Programming Tips
- » Computability, Complexity, and Theory - Georgia Tech
- » Google Developer Day Keynote
- » In-core computation with HyperBall
- » 소프트웨어 개발의 이해를 돕기 위한 비유
- » Redmine Plugin Installation
- » Work Breakdown Structure (WBS)
- » Wearable Technology Trends in 2016
- » Software Engineering Principle 3
- » Software Engineering Principle 2
- » Software Engineering Principle 1
- » KIWI Installation
- » IntelliJ IDEA 15
- » Maven Support in IntelliJ IDEA
- » CUDA LLVM Compiler
- » Stanford Compilers Course
- » Unit Test using specs
- » Scala to Java
- » Privacy as a Practice in Mobile App Development
- » Function Composition
- » Scala Collection
- » Rethinking SIMD Vectorization for In-Memory Databases
- » Scala idiom - Prefer immutable data structures
- » Scala - Tools and Frameworks
- » Scala - Pattern Matching
- » Scala - Functional/Collection
- » Why Scala?
- » Introduction to Scala
- » Scala - Object Oriented Features
- » Scala Installation
- » Scala Basics
- » SBT (Simple Build Tool)
- » Dependency Injection
- » GNUPlot Basics
- » Google Protocol Buffer Basics - Java
- » 11 Core Big Data Workload Design Patterns
- » How to fix “System program problem detected” error on Ubuntu
- » Samsung Developer Day 2014 at MWC - Samsung MultiScreen SDK
- » Unit Test
- » Open Source Analysis Tips
- » Functional Specifications
- » Burndown Chart
- » Bigtable
- » Chubby
- » The Google File System (GFS)
- » PageRank Algorithm
- » Overview of Data Storage and Coordination Services
- » Underlying Communication Paradigms
- » PageRank History
- » Overall Architecture and Design Philosophy
- » Bloom Filter
- » Using Gitlab on Mac OS X
- » Gitlab Installation on Mac OS X
- » Why Functional Programming?
- » Macport Commands Summary
- » Wiki Tutorial
- » Scrum Events
- » Introduction to the Maven
- » Native C/C++ Like Performance For Java Object Serialization
- » Using ByteBuffer in Java
- » Effective Team Membership
- » Confluent and Functional Persistence
- » Full Persistence
- » Partial Persistence
- » Persistent Data Structures
- » Scatter plots in Python
- » Generating random numbers and plots in Python
- » JUnit, A Tool for Test-Driven Development
- » Syntax highlighting tools for github page
- » Boxplots comparing two different populations in Python
- » Sequence Diagram
- » JAXB Class Generation From XML Schema File using JAXB Tool
- » My Scoop It! Sites
- » Concurrent Bug Patterns and How to Test Them
- » Introduction to Bug Patterns in Java
- » Foundational data architecture patterns
- » N-Screen Application Development Manual
- » Android WebView Application using Naver Open API
- » Filter pattern
- » Agile Project Management
- » Agile Processes and Scrum
- » Git Commands
- » Git Concepts and Architecture
- » Adding a post to github page
developments
- » Technology Scouting and Innovation Ecosystems
- » Impact of Technological Innovation on Industrial Ecosystems
drug discovery
- » From Scientific Skills to Verified Lab Workflows
- » From Evidence Paths to Falsifiable Rules
- » Tri-State Neuro-Symbolic AI Co-Scientist for Drug Discovery
- » Reliable AI Co-Scientists for Drug Discovery
- » From Traceable SBDD to RNA Foundation Tools
- » From Evidence Lineage to Scientific Self-Audit
- » From Multi-Model Collaboration to Enterprise Drug Discovery
- » Causally Revisable Epistemic Neuro-Symbolic Co-Scientist
- » From Plausible Correlations to Falsifiable Scientific Beliefs
- » Experience-Grounded Drug-Discovery AI Co-Scientist
- » Stereochemistry at Tetrahedral Centers
- » From Co-Folding Accuracy to Physics-Grounded Agentic Drug Design
- » From Atoms to Acids: The Structural Language of Organic Chemistry
- » Epistemic Molecular World Model for Self-Improving AI Co-Scientists
- » Decision-Centric Epistemic AI Co-Scientist for Drug Discovery
- » Aromatic Compounds: Resonance, Electrophilic Substitution,...
- » Alkenes, Alkynes, and Reaction Mechanisms
- » Reactions of Alkenes and Alkynes
- » The Structural Logic of Organic Compounds
- » Execution-Grounded Multimodal Drug-Discovery Co-Scientist
- » Execution-Grounded Epistemic Neuro-Symbolic Co-Scientist
- » Self-Improving Experimental AI Co-Scientist for Drug Discovery
- » Agentic Hit Discovery: The First Phase for Agentic AI Drug Discovery
- » Epistemic Scientific Autonomy: Molecular LLM Agents and K-Bench
- » Agentic AI Drug Discovery Platform: An Implementation Blueprint
- » Vecura and the Rise of Agentic AI Co-Scientists
- » Five Shifts Toward Evidence-Grounded Closed-Loop Discovery
- » Structure-based drug design and explainable AI
- » Post-IsoDDE: Selection, Ranking, and State Awareness
- » A Structural Atlas of Kinase-Ligand Interactions for Drug Discovery
- » Graph Neural Networks and Drug Interactions
- » Artificial Intelligence in Drug Discovery
- » From AI Co-Scientists to Closed-Loop Drug Discovery
- » Piece-based design and scaffold hopping
- » Equation-Discovering Physics-Grounded AI Co-Scientists
- » Biopharmaceuticals, Cell and Gene Therapy, and AI
- » AI monitoring of clinical outcomes and adverse reactions
- » AI Combating Antibiotic Resistance
- » The Convergence of AI and Quantum Computing — Two Filters
- » AI Medical Imaging for Precision Drug Design
- » A Structural Informatics Guide to Kinase Selectivity...
- » From Binary Interaction Fingerprints to a Multimodal Kinase Atlas
- » An Evidence-to-Prediction Stack for Kinase Drug Discovery
- » Selecting Medication using Electronic Medical Records and ML
- » Boltz: From Physical Steering to Synthesis-Aware Molecular Design
- » OpenDDE: From All-Atom Structural Reasoning to an Open Drug Discovery Engine
- » IsoDDE Trends: From Bigger Cofolding Models to Generalization-Aware Closed-Loop Drug Design
- » Large-scale language models and drug target discovery
- » Patient Stratification and Precision Medicine
- » PRISM-DDE: Physics-Grounded and OOD-Robust Drug Design
- » Alzheimer's Precision Treatment
- » Integrating AI in pharmacovigilance and clinical trial monitoring
- » The Challenges of Vaccine Development and AI
- » Counterfactual explainability in AI-driven drug discovery
- » Blockchain and AI in drug development
- » 'AlphaFold 4' — DeepMind drug spin-off's private AI
- » From discovery to global distribution
- » Bias and transparency in AI and machine learning models for drug design
- » Generative artificial intelligence for de novo drug design
- » AI Accelerating Vaccine Development
- » Artificial intelligence for drug repurposing
- » An AI and ML tool in cancer drug development and immunotherapy
- » KLIFS — Can only be compared by measuring with the same ruler
- » AI Innovation in Neuroscience
- » AI-powered genomic medicine: Technologies and challenges
- » AI and machine learning for disease pathway modeling
- » AI in Cancer Drug Development and Immunotherapy
- » AI in multi-omics integration for precision drug design
- » Leveraging AI for integrating genomics, transcriptomics, and proteomics
- » AI based toxicity prediction: Advancing drug safety and risk assessment
- » AI Network-based Drug Repurposing
- » AI-powered In silico ADMET modeling and optimization in drug design
- » AI for predicting drug-likeness and bioavailability
- » AI for predicting pharmacokinetics and pharmacodynamics
- » AI-based network pharmacology
- » AI in molecular screening: Advances, challenges, and future perspectives
- » AI-based drug repurposing in precision medicine
- » Metaphors of medicine
- » Ethical implications of AI in precision drug design: A philosophical inquiry
- » Case study of returning docking results to a knowledge graph
- » AI-based drug repurposing and combination therapy
- » Epistemological challenges in AI-driven drug discovery
- » AI in drug design: A historical and future perspective
- » Biomedical Literature Vector DB for Agentic RAG
- » ADMET Prediction: The Journey of Molecules Through the Body
- » The Intelligence to Read Molecules as Language
- » AI-based discovery of new therapeutic modal drug candidates
- » Qualitative Transformation of ChEMBL-based Hit Selection
- » CLADD Framework: Multi-Agent-Based Drug Discovery
- » AlphaProof Nexus: Innovation in AI-based Mathematics Research
- » Agentic RAG: Medical Exploration and Evidence-Based Search Agent
- » Wet-Lab Automation for AI-Based Drug Development
- » Biology-Inspired AI & Organic Learning
- » Multimodal RAG and Simulator Integration Architecture
- » AI-based Autonomous Scientific Discovery
- » Safety Challenges and Solutions of Recursive Self-Improvement
- » Episodic Memory-Based Continual Learning in Science-Specific LLMs
- » LLM Research Specialized for New Drug Development
- » Research Trends in Simulator-Linked Agent RAG Architecture
- » Redefining Drug Discovery with TxGemma
- » Causal Inference AI Innovation in Drug Discovery
- » Drug Development Innovation: TxGemma and Hyper-Relational KG
- » Computer Graphics Research Trends in Drug Development
- » Strategic Drug Repurposing Analysis using ChEMBL Mechanism Data
- » TxGemma-based Agentic AI: Hyper-Relational KG Drug Development
- » ChEMBL Data-Driven AI Drug Development Strategy
- » ChEMBL Database Schema and Drug Discovery Utilization Guide
- » Integrating ChEMBL with TxGemma and Agentic-Tx
- » Public Benchmark Datasets for AI-Driven Drug Discovery
- » Comparative Analysis of AI Models for Drug Discovery
- » New Drug Development Research Dataset
- » Bioinformatics-Based Structure-Based Drug Design (SBDD)
- » Innovation and Future of AI-Based Lead Optimization
- » Inverse Molecular Design and Future Directions
- » Innovation in AI-Based Drug Development
- » Innovation in Drug Discovery: The AI-Driven Reverse Design Paradigm
- » Strategic Framework of In-Silico Drug Discovery
- » Hit Identification and Virtual Screening
- » Innovation in Target Identification and Validation
- » Drug Development Using LLM-based Biomedical Knowledge Graphs
- » Opening the Future of New Drug Development by Connecting Data
- » GNN-Based Biomedical Knowledge Graph Mining
- » A Paradigm Shift In New Drug Development
- » The AI Revolution in Drug Discovery
- » GLP-1 - A New Frontier in Modern Medicine
foundation models
- » Pretraining for Deep Learning Theory
- » Personalized Auto-Research: Towards a True AI Co-Scientist
- » Neural Networks as Function Approximators
- » Large Language Models for Artificial General Intelligence
- » Improving the Matrix Multiplication Exponent with Modern Optimization
- » How Far Are We From AGI: Are LLMs All We Need?
- » Deep Linear Networks at Initialization
- » OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
- » Mathematics in the Age of AI
- » Richard Sutton's Bitter Lessons and Continuous Learning
- » Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
- » ASI-Bench: Measuring Scientific Autonomy Beyond Human Methodological Guidance
- » Training AI Scientists to Replicate Research
- » Intern-S2-Preview: Building a Scientific Agentic Foundation Model
- » RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
- » PRISM-DDE: Physics-Grounded and OOD-Robust Drug Design through Interventional Reasoning, Ensemble Sampling, and Multi-Objective Generation
- » IsoDDE: From Biomolecular Structure Prediction to a Computational Drug Design Engine
- » Evo-Bench: Can Language Models Improve Agent Harness?
- » Designing and Evaluating an Agentic RAG System for a Domain-Specific Research Archive
graph mining
- » Epilogue — Reflections on the Journey and Closing Remarks
- » Graph Research: SIGMOD, VLDB, ICDE, and TKDE
- » Deploying Your Application on the Google Cloud
- » Choosing the Right Cloud Platform for GenAI Applications
- » Creating an Intelligent Recommendation System
- » Integrating LangChain4j and Spring AI with Neo4j
- » Constructing a Recommendation Graph with H&M
- » Qualifier-Aware Approximate Scientific Reasoning
- » Introducing the Neo4j Spring AI and LangChain4j Frameworks
- » From Output-Sensitive Indexing to Partial-Order Motif Estimation
- » Exploring Advanced Knowledge Graph Capabilities with Neo4j
- » Science does not end with a single correct answer.
- » Adding AI-Powered Search with Haystack
- » Rethinking Temporal Knowledge Graph Representation Learning: From Entities to Evolutionary Event-Centric Clusters
- » Building a Movie Knowledge Graph with Neo4j
- » Building a QA Agent with LangGraph
- » Improving Enzyme Prediction with Chemical Reaction Equations by Hypergraph-Enhanced Knowledge Graph Embeddings
- » Building Knowledge Graph Foundations
- » Asking a KG Questions with Natural Language
- » Demystifying RAG
- » Knowledge Graph-Powered Retrieval-Augmented Generation
- » Introducing LLMs, RAGs, and Knowledge Graphs
- » Node Classification and Link Prediction with GNNs
- » Analyzing Text Data with Deep Learning
- » From Knowledge Graphs to Knowledge Lakes
- » Graph Representation Learning and Graph Neural Networks
- » Talking to Your Knowledge Graph
- » Graph Feature Engineering: Manual and Semiautomated Approaches
- » Semantic Search and Similarity
- » Machine Learning on Knowledge Graphs: A Primer Approach
- » Dependency Knowledge Graphs
- » NED with Open LLMs and Domain Ontologies
- » Where are data mining societies heading?
- » Pattern Detection Knowledge Graphs
- » Named Entity Disambiguation
- » Identity Knowledge Graphs
- » Building Knowledge Graphs with Large Language Models
- » Mapping Data with Metadata Knowledge Graphs
- » Extracting Domain-Specific Knowledge from Unstructured Data
- » Graph-Native Machine Learning
- » From Simple Networks to Multisource Integration
- » Scalable Temporal Graph Neural Network Training on Dynamic Graphs
- » Enriching Knowledge Graphs with Data Science
- » Create Your First Knowledge Graph from Ontologies
- » Distributed Graph Neural Network Training
- » Integrating Knowledge Graphs with Information Systems
- » Intelligent Systems: A Hybrid Approach
- » Accelerating Computation for Scalable Graph Neural Network Training
- » Loading Knowledge Graph Data
- » Knowledge Graphs and LLMs: A Killer Combination
- » Reducing Data Transfer for Scalable Graph Neural Network Training
- » Language of Drug Discovery & ChEMBL Field Guide
- » Graph Databases: Cypher - Graph Query Language
- » KDD 2026: Research Papers
- » Preliminaries: Graph Neural Network Training
- » Organizing Principles for Building Knowledge Graphs
- » Introduction to Graph Neural Network Training on Large Graphs
- » Introducing Knowledge Graphs
- » Temporal Simple Path Graph (tspG) Generation Algorithm
- » Enterprise-Scale Biomedical Knowledge Graphs and GraphRAG Systems
- » Analysis of Restless Reachability Algorithms in Temporal Graphs
- » In-Context Learning & Hyper-Relational Knowledge Graphs
- » TxGemma-based Agentic AI: Hyper-Relational KG Drug Development
- » Converging Advances to Accelerate Molecular Simulation
- » Learning Delaunay Surface Elements for Mesh Reconstruction
- » Knowledge Graphs Seminar
- » Data Cataloging with Knowledge Graphs
- » The Foundation of a Data Fabric
- » Data Mesh, Data Fabric, Data Lakehouse
- » Tractable Probabilistic Circuits
- » Distributed Analytical Database Systems
- » GraphZeppelin - Streaming Graph Connectivity at Scale
- » Understanding Graph Data Representations in Triplestores
- » Graph-Powered Data Exploration
- » Google BigQuery
- » Conformal Prediction Tutorial
- » Traffic Prediction Paper Collection
- » End-to-end Optimization of Machine Learning Prediction Queries
- » Compute Complex Temporal Join Queries Efficiently
- » Making Learned Query Optimization Practical
- » Universal Database Optimizer
- » Machine Learning for Query Optimization
- » ML Explainability
- » Towards Generalizable Autonomy
- » Building an AI and ML ready Modern Data Platform
- » Diffusion Probabilistic Modelling of Protein Backbones in 3D
- » ICCV Authors Guidelines
- » Diffusion Probabilistic Models
- » Stable Diffusion - What, Why, How?
- » Deep Energy-Based Learning
- » Incident Prediction in Spatio-Temporal Road Graph Networks
- » Diffusion probabilistic modelling of protein backbones in 3D
- » Contrastive Learning in PyTorch
- » Neural Rendering
- » Anatomy of a Research Paper
- » Geometric Deep Learning for Drug Discovery
- » Deploy Custom Python Model Server
- » Contrastive Learning in PyTorch
- » InferenceService using a Custom Torchserve Image
- » From Machine Learning to Autonomous Intelligence
- » Towards a Learned Index Structure for ANN Search
- » Graph Processing; from Academic Research to Industrial Application
- » Katana Graph; A Graph Intelligence Platform
- » Machine Learning for Scientific Discovery
- » Graph Neural Networks as Gradient Flows
- » Ab-Initio Potential Energy Surfaces
- » Reinforcement Learning via Sequence Modeling
- » Recipe for a General, Powerful, Scalable Graph Transformer
- » Spatial Hash Grids & Tales from Game Development
- » Cardinality Estimation Benchmark
- » Spatial Indexing in PostGIS
- » Data-driven Learned Metric Index; an Unsupervised Approach
- » Synopses - Samples, Histogram, Wavelets and Sketches
- » Query Execution in MonetDB
- » Low overhead self-optimizing storage for compression
- » A Database Tuning Tool that "Reads the Manual"
- » Rethinking Graph Transformers with Spectral Attention
- » Introduction to TorchServe
- » MicroK8s Installation & Simple Commands
- » Diffusion Models from Scratch in PyTorch
- » Deep Learning Theory Lectures
- » Kubeflow Fairing
- » Kubeflow Fairing, Pipelines, and Training
- » On Recoverability of Graph Neural Network Representation
- » Deploy Model to KServe
- » TorchScript and PyTorch JIT
- » Spectra of Graphs and Hypergraphs
- » How to Serve PyTorch Models with TorchServe
- » A Novel Data Set for Information Retrieval on the Basis of Subgraph Matching
- » Graph Embedding in Vector Spaces Using Matching-Graphs
- » Google Cloud BigQuery ML Using SQL
- » Open World Lifelong Learning
- » On Machines that can Learn Continually
- » Introduction to Continual Learning
- » Introducing OpenAPI Generator
- » Kubeflow Development Environment
- » KFServing Deep Dive
- » Protein structure prediction with AlphaFold
- » Deep Learning for Scientific Computation
- » Started with AI in Drug Discovery
- » Istio Simplified
- » Knative and Microk8s with Multipass
- » KServe in Kubenetes
- » Graph Ordering Attention Networks
- » Introduction to KServe
- » Position-Aware Graph Neural Network using Reachability Estimations
- » Isomorphism Using Adjacency Matrix
- » Efficient Probabilistic Truss Indexing on Uncertain Graphs
- » Toward Verified Artificial Intelligence
- » Modern Data Stack
- » PyTorchJobClient
- » KServe (Kubeflow KFServing) Live Coding Session
- » Workflow for ML Projects — MLOps
- » Kubeflow Setup
- » Introduction to Data Mesh
- » Theory of Graph Neural Networks
- » Representational Power of Graph Nerual Networks
- » Task structure and generalization in graph neural networks
- » Geometry Processing with Neural Fields
- » Trends in AI
- » RelationalAI Knowledge Graph Management System
- » Topological Graph Neural Networks
- » Causality and (Graph) Neural Networks
- » Using Graph Neural Networks for Multi-Node Representation Learning
- » Epistemic Uncertainty Estimation for Efficient Search of Drug Candidates
- » Toward Neuro Causality
- » Connect to MySQL Database from Visual Studio Code
- » Data-Efficient Graph Grammar Learning for Molecular Generation
- » Rethinking Graph Transformers with Spectral Attention
- » How GNNs and Symmetries can help to solve PDEs
- » Neural diffusion PDEs, differential geometry, and graph neural networks
- » BigQuery ML; Machine Learning with Standard SQL
- » GNN with Learnable Structural and Positional Presentations
- » Istio Service Mesh 101
- » Graph Neural Networks and Diffusion PDEs
- » Recommender Systems using Graph Neural Networks
- » Manage Multi-tenant ML Workloads Using Istio
- » Graph Neural Networks as Neural Diffusion PDEs
- » Exploring ML Model Serving with KServe
- » Kubeflow Tutorial | Model Serving
- » Using AI to accelerate scientific discovery
- » Java to MySQL using Visual Studio Code
- » Developing the Kubernetes Python Client
- » Kubernetes Patterns
- » Using Visual Studio Code for Java Maven Project
- » Mapping External Services
- » MiniKF; Kubeflow on your laptop
- » Gateway Routing Pattern
- » Kubeflow v1.5 Release Overview
- » TensorFlow Distributed Training on Kubeflow
- » Sidecar Pattern
- » YAML
- » Kubeflow on macOS
- » Why is Kubernetes called K8s?
- » Kubernetes Crash Course for Absolute Beginners
- » Marrying Top k with Skyline Queries
- » Spatial Skyline Queries on Triangulated Irregular Networks
- » Challenges and Solutions of Using Kubernetes for Blockchain Applications
- » PyTorch Training (PyTorchJob)
- » Kubeflow Architecture
- » Istio and Service Mesh
- » Kubernetes Tutorial for Beginners
- » Serving Machine Learning Models at Scale Using KServe
- » Advanced Model Inferencing Leveraging Kubeflow Serving
- » PyTorch via SQL Commands
- » Scaling Shortest Path Graph Queries on Very Large Networks
- » Hierarchical Core Maintenance on Large Dynamic Graphs
- » Shortest Paths and Centrality in Uncertain Networks
- » Bag of Tricks for Node Classification with Graph Neural Networks
- » The Case for Learned Index Structures
- » Deep Learning for Graph Similarity Search
- » HyperSPNs; Compact and Expressive Probabilistic Circuits
- » Learned Index Structures for Dynamic and Multi-Dimensional Data
- » Blame the Data, Not the System
- » Hyperbolic Embeddings in Machine Learning and Deep Learning
- » What are Temporal Databases?
- » Git Commit Message Style Guide
- » What is PrestoDB?
- » Spatial, High Dimensional, Temporal Data Indexing and Querying
- » A Learned Spatial Index for Range and kNN Queries
- » An Introduction to Spatial Data and its Applications
- » Robustness/Interpretability in Vision & Language Models
- » Visual Data Analysis; How? When? Why?
- » SageDB; A Self-Assembling Database System
- » Towards Zero-Shot Learning for Databases
- » From Workload-Driven to Zero-Shot Learning
- » From Notebook to Kubeflow Pipelines to KFServing
- » Improving Transfer and Robustness of Supervised Contrastive Learning
- » Approximate Query Processing
- » What are Probabilistic Data Structures?
- » Approximation Algorithms for Large Scale Data Analysis
- » Modeling Relational Data with Graph Convolution Network
- » Open-source Change Data Capture With Debezium
- » Finding Approximately Repeated Patterns in Time Series
- » Looper; An End-to-End ML Platform for Product Decisions
- » Learned Indexing and Sampling for Improving Query Performance
- » Principles of Good Machine Learning Systems Design
- » Deep Learning Design Patterns
- » Tips for Thinking Like a Machine Learning Architect
- » Machine Learning Design Patterns
- » Introduction to Kubeflow
- » Martingale Theory
- » Making Architecture Matter
- » Bayesian Inference for Big Data
- » Architecture and Cardinality Estimations for Graph Queries
- » What causes congestion?
- » Optimization problems in graphs with locational uncertainty
- » Deep Implicit Layers
- » Convex Functions
- » Quantum Deep Learning
- » Uncertainty and Out-of-Distribution Robustness in Deep Learning
- » Probabilistic Methods for Increased Robustness in Machine Learning
- » Probabilistic Circuits - Representations, Inference, Learning and Theory
- » FLAT-Fast, Lightweight and Accurate Method for Cardinality Estimation
- » Learned Query Scheduling
- » A 10 Minute Introduction to Kubeflow
- » Ethics of Artificial Intelligence
- » What is AI Ethics?
- » What is the Cardinality Estimator?
- » Qd-tree - Learning Data Layouts for Big Data Analytics
- » Sum-Product Networks
- » Towards Zero-Shot Learning for Databases
- » Machine Learning Design Patterns
- » Learned DBMS Components 2.0
- » Deep Multi-task and Meta Learning
- » Machine Learning Design Patterns - Rebalancing
- » Calcite Tutorial
- » NeuroCard - One Cardinality Estimator for All Tables
- » GNN based Recommender Systems
- » On the Nature of Data Science
- » Breaking the Limit of Graph Neural Networks using Local Mixing Patterns
- » Performance Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks
- » Data Fabrics for Enterprise Data Management?
- » Query Optimization and Acceleration at Dremio
- » AI4DB & DB4AI-Papers
- » Permissioned Blockchains
- » Apache Spark, Data Science + Machine Learning
- » Introduction to Temporal Graph Neural Networks
- » Traffic Forecasting with Pytorch Geometric Temporal
- » Geometric Deep Learning
- » What Is NFT? - Non Fungible Token
- » Deep Recommender Systems
- » Weisfeiler and Lehman Go Cellular; CW Networks
- » Matrix Multiplication, and the Asymptotic Spectrum Of Tensors
- » Traffic Prediction for Intelligent Transport System
- » Revisiting Knowledge Graph Completion From a Practical Perspective
- » Applying Machine Learning-based Database Tuning in Production
- » Cloud-Native Ledger Graph Database
- » A Probabilistic Model for Joint Inference from Differential Equations
- » Optimization Frameworks for Graph Clustering
- » Neuralising a Computer Scientist
- » Preparing For Your Dissertation Defense
- » Oral Dissertation Defense Preparation
- » How To Defend Your Thesis? Top 10 Tips For Success
- » How to Get a PhD in Computer Science
- » 100 Thesis Defense Questions in 3 Categories
- » 10 Mistakes to Avoid When Defending Your Thesis
- » How to prepare for your PhD thesis defence
- » Geometric Deep Learning-Past, Present, And Future Optimization
- » Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
- » How to write a literature review - my simple 5 step process!
- » Geometric Deep Learning - from Euclid to drug design
- » Graph Isomorphism in Quasipolynomial Time
- » Geometric Deep Learning Blueprint
- » Geometric Deep Learning-The Erlangen Programme of ML
- » KDD Cup OGB Large-Scale Challenge
- » Theoretical Foundations of Data-Driven Algorithm Design
- » Relational Inductive Biases, Deep Learning, and Graph Networks
- » The Future Is Big Graphs
- » The Universal Approximation Theorem
- » Equivariant Networks and Natural Graph Networks
- » An Introduction to Hamiltonian Monte Carlo Method for Sampling
- » Recurrent Neural Networks for Cognitive Neuroscience
- » Permutation Equivariance of Graph Filters
- » Graph Convolutional and Isomorphism Networks
- » Combinatorial Properties of the Weisfeiler-Leman Algorithm
- » Advances in Self-Supervised Learning
- » Contrastive Loss, Deep Metric Learning
- » Self-Supervised Learning
- » Contrastive Learning; A General Self-supervised Learning Approach
- » Supervised Contrastive Learning
- » What is Noise-Contrastive Estimation?
- » GNNs with Learnable Structural and Positional Representation
- » Knowledge Graph Representation
- » Temporal Graph Networks (TGN)
- » Building a Recommender System using Graph Neural Networks
- » Junction Tree Variational Autoencoder for Molecular Graph Generation
- » Understanding Graph Attention Networks
- » GVAE Training and Adjacency Reconstruction
- » Graph Representation Learning for Drug Discovery
- » Graph Neural Networks for Traffic Prediction
- » Visual Exploration of Trajectory Data
- » GPS Data Analysis with Python
- » 22 Python libraries for Geospatial Data Analysis
- » Clustering Trajectories
- » Towards Causal Representation Learning
- » Random Sum Product Networks
- » Understanding & Generating Source Code with Graph Neural Networks
- » Sum-Product Networks; The Next Generation of Deep Models
- » Deep Learning to Discover Coordinates for Dynamics
- » The Power of Graph Signal Processing
- » Some Mathematical Problems in Graph Signal Processing
- » On Laplacian Eigenmaps for Dimensionality Reduction
- » Overview of Graph Embeddings
- » Sum-Product Networks; Powerful Models with Tractable Inference
- » Sum-Product Networks
- » Geometric Deep Learning and Reinforcement Learning
- » Discovering Genetic Medicines with our AI Drug Discovery Platform
- » Proof of Euler's Formula
- » GNNs and RL in Traffic Optimization in Cities
- » Graph Neural Networks and Applications to Deep Reinforcement Learning
- » Writing Scientific Papers
- » Drug Discovery with GANs
- » PyTorch nn.Embedding()
- » Reproducing Kernel Hilbert Spaces
- » Dynamical Systems and Machine Learning
- » An Introduction to Hilbert Spaces
- » Graph Neural Networks in Computational Biology
- » What is Euler's Number 'e'?
- » Euler's Formula
- » The Characteristic Equation and Eigenvalues
- » Spanning Trees and Kirchhoff's Theorem
- » Acceptance Rate of AI Conferences
- » Deep Graph Learning Foundations, Advances and Applications
- » Learning Graphs from Data; A Signal Processing Perspective
- » Making Graphs Compact by Lossless Contraction
- » A Short Course in Spectral Graph Theory
- » An Introduction to Spectral Graph Theory
- » Spectral Graph Theory; Enter Linear Algebra
- » Spectral Graph Theory; The Standard Random Walk
- » Spectral Graph Theory; The Quadratic Form
- » The Laplacian Matrices of Graphs; Algorithms and Applications
- » Pragmatic Ridge Spectral Sparsification for Large-Scale Graph Learning
- » Knowledge Graph Embeddings Tutorial; From Theory to Practice
- » How to use edge features in Graph Neural Networks
- » Graph Representation Learning
- » Papers on Graph Neural Networks
- » A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation
- » Super-Constant-Pass Streaming Lower Bounds for Reachability
- » Awesone Neural ODE
- » Neural Differential Equations
- » Generative Adversarial Networks and TF-GAN
- » Fairness and Bias in Algorithmic Decision-Making
- » A Learned Sketch for Subgraph Counting
- » Learning over sets, subgraphs, and streams
- » Categorical Reparameterization with Gumbel-Softmax
- » A Deterministic Parallel APSP Algorithm and its Applications
- » How Do You Generate Synthetic Data?
- » Synthetic Tabular Data Generation
- » Decremental All-Pairs Shortest Paths in Deterministic Near-Linear Time
- » Streaming Lower Bounds for Reachability
- » Learning Deep Matrix Factorizations Via Gradient Descent
- » NVIDIA Omniverse and a Future of Shared Worlds
- » Introduction to Graph Neural Networks
- » CVPR 2021 Workshop on Autonomous Vehicles
- » Pytorch-BigGraph: A Large Scale Graph Embedding System
- » Unsupervised Intelligent Agents
- » Uncertainty, causality and generalization
- » Illustrated Guide to RNN, LSTM, and Transformers
- » Banach Space Representer Theorems for Neural Networks
- » Next-Generation Recurrent Network Models
- » Graph Representation Learning for Drug Discovery
- » PostgreSQL Optimizer Methodology
- » PPRGo-Scaling Graph Neural Networks with Approximate PageRank
- » The Energy-Based Learning Model
- » But how does bitcoin actually work?
- » Explainable AI Cheat Sheet - Five Key Categories
- » Digital Twins and Geospatial Data
- » Trends in Traffic Prediction
- » Understanding Competencies
- » Scaling Up Graph Neural Networks to Large Graphs
- » Inductive Logic Programming
- » Useful Resources for Traffic Prediction
- » A Video Game That Looks Like Reality!
- » Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
- » New lower and upper bounds for quantile summary algorithms
- » Data Summarization for Machine Learning
- » Position aware Graph Neural Networks
- » Instacart Data Description
- » Fast Counts on Big Data Systems
- » MonetDB; Scale Up Before You Scale Out
- » Kronecker Graphs, Data Generation, and Performance
- » AI+VR; The Kayfabe Life
- » Efficient Query Processing Using Machine Learning
- » How to use mathcha math online editor
- » Uncertainty estimation in supervised learning
- » Approximately Bayesian Ensembling
- » Efficient Data Processing on Modern Hardware
- » AI Bias and Fairness
- » Generative Models for Graphs
- » Evidential Deep Learning and Uncertainty
- » Learned Approximate Query Processing
- » Meta Learning Tutorial
- » Deep Learning Outline
- » Transfer Learning
- » Approximate nearest neighbor search in high dimensions
- » Learning-Based Sketching Algorithms
- » Deep Learning Under Distribution Shift
- » Principles for Tackling Distribution Shift
- » Scalable Graph Neural Networks with Deep Graph Library
- » Deep InfoMax
- » Introduction to Bandits in Recommender Systems
- » Our paper has been published in IEEE Access!
- » Constant Girth Approximation for Directed Graphs in Subquadratic Time
- » Conditionally optimal approximation algorithms
- » Sparsification of Graphs and Matrices
- » MapGraph
- » Stanford Network Analysis Platform(SNAP)
language models
liberal arts
- » How do we find good books?
- » Korea Summit 2018
- » Why we learn?
- » How To Read a Scientific Research Paper
- » How to Write a Research Plan
- » Just Do It
- » Conferences 2018
- » 중세 과학
- » 고대 과학
- » 학교와 직장의 차이점
- » Tell Me About Yourself - A Good Answer to This Interview Question
- » PhD Interview Questions
- » How to Improve your Clarity of Thought
- » How to Prepare and Deliver a Great TED talk
- » IELTS & TOEFL Writing - 5 Common Mistakes
- » 일상으로의 초대
- » 아주 짧은 인생을 가치 있게 보내는 법
- » Automatic Source Transformation from C++ to CUDA using Clang/LLVM
- » 그댄 행복에 살텐데
- » The 5 Leadership Styles
- » 등록금 0원
- » Emotional Intelligence
- » Studying in Germany
- » 민물장어의 꿈
- » Research Topics in Database Management
- » IEEE NetSoft 2016 Call for Demonstrations
- » Sparks of Genius
- » Papers in Parallel and Distributed Data Management
- » If today were the last day
- » Telling a Story
- » The Scope of a Paper
- » Map-D
- » Main Memory and Streaming Databases
- » Think Fast, Talk Smart
- » Calendar of Computer Graphics Events
- » LaTeX Fonts on Mac OS X
- » Proceedings of the VLDB Endowment, Volume 9
- » Research Posters 101
- » A GPU Parallelized Database Accelerator
- » Steve Jobs' Last Words
- » 12 Habits of Extraordinarily Motivated People
- » Writing-up Qualitative Research
- » Bad Boys Blue Collection
- » How To Read A Paper
- » Paper Writing Strategy
- » Paper Writing
- » ACM TODS Manuscript Preparation
- » 우리는 왜 우리가 되지 못하는가?
- » Distributed Computing Conferences
- » IEEE Transactions on Knowledge and Data Engineering
- » How Google Works
- » Summarizing
- » How to Write a Good Paper
- » What is Visual Thinking?
- » Ordeal
- » Einstein and Buddhism
- » CV vs. Resume
- » You've got to find what you love
- » What You're Really Meant to Do
- » Logotherapy
- » Today
- » Mathematical Universe?
- » The Power of Inquiry to Spark Breakthrough Ideas
- » A More Beautiful Question
- » Categorical Imperative
- » Ballad Music Collection
- » Discussion
- » The School of Athens
- » Common Lisp using LLVM and C++ for Molecular Metaprogramming
- » Big Data Challenges and Opportunities
- » Darwin Day 2015 Questions
- » How to Read a Technical Paper
- » SIGMOD 2015 Papers
- » A well-planned kickoff meeting sets the tone for a successful project
- » Seven Key Elements for a Successful Kickoff Meeting Agenda
- » Cornell Notes
- » Writing An Author Bio
- » How to Write a Paper Efficiently
- » How to Prepare for Your Performance Review Meeting
- » Passion
- » Effective Meeting Strategy
- » Research skills
- » Steve Jobs - One Last Thing
- » Camino and Hope
- » Camino, Dream and Choice
- » Creativity in Business
- » A Thousand Dreams of You
- » Such a Man
- » The Selfish Gene
- » 10 Usability Heuristics for User Interface Design
- » Folder Management
- » Computer Science @ University of Cambridge
- » How to Share a Bread Evenly
- » 24 Live Another Day
- » Steve Jobs at SIGGRAPH 1995
- » MapReduce and Hadoop Papers in the VLDB
- » MapReduce and Hadoop Algorithmic in Academic Papers
- » Conduct Research Survey
- » Stream Data Processing for Performance Evaluation of the Equipment in an Offshore Plant
- » Papers about MapReduce
- » Chest aching Story
- » Like a star
- » TDD Best practices
- » Test-Driven Development in a nutshell
- » Let it go
- » Randy Pausch Last Lecture, Achieving Your Childhood Dreams
- » Sunflower
- » A Flying Butterfly
- » Synchronization among Heterogeneous Distributed Objects
- » How to write a good research paper
- » Impressionist Tutorial
- » Introduction to Impress.js
- » How to overcome common obstacles to publishing in English
- » Publications
- » Open The Door
- » Characteristics of the Smart Devices
- » How to play the piano in a week
- » Smile Again
- » Logical Communication-based Middleware for Collaboration among Smart Apps in P2P Network Environments
- » The Presentation Secrets of Steve Jobs
- » Paper Organization
- » Wisdom from Steve Jobs
machine learning
- » Compute-Matched Scaling Laws for MoE Looped Transformers
- » Large Language Models as a Cognitive Virus
- » Rethinking KV Cache Eviction for Efficient Reasoning
- » Joint Harness-Weight Optimization for Agentic Language Models
- » Agentic Knowledge Workflows, and Production-Ready AI
- » Fast Weight Attention for Continual Learning
- » VLDB 2026 Data Systems Watch: The Rise of Agentic Data Systems
- » Temporal Graph Analytics with Architecture-Aware Version Skipping
- » LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
- » Adaptive Temporal Variable Ordering for Graph Joins
- » Bayesian Uncertainty and AI Architectures for AGI
- » Visual General Intelligence: A White Paper
- » Code World Model: Coding Agent as World Brain
- » Post-IsoDDE: Selection, Ranking, and State Awareness
- » A Structural Atlas of Kinase-Ligand Interactions for Drug Discovery
- » Graph Research: SIGMOD, VLDB, ICDE, and TKDE
- » Artificial Intelligence in Drug Discovery
- » A Comprehensive Survey on Symbolic Regression
- » Agentic Data Systems: From LLM Applications to Database-Native Agents
- » The End of Training at Finite Width
- » Residual Learning Through Effective Theory
- » Initializing Deep Learning Theory
- » Information in Deep Learning
- » RG Flow of Preactivations: A Finite-Width Theory of Deep Networks
- » RG Flow of the Neural Tangent Kernel
- » Representation Learning at Finite Width
- » Kernel Learning at Infinite Width
- » Gradient Descent and the Neural Tangent Kernel
- » Criticality, Universality, and the Depth-to-Width Scale in Deep Networks
- » Criticality of the Neural Tangent Kernel
- » Bayesian Learning in Deep Neural Networks
- » Pretraining for Deep Learning Theory
- » Personalized Auto-Research: Towards a True AI Co-Scientist
- » Neural Networks as Function Approximators
- » A Unified Schema Matching Framework with Large Language Models
- » Large Language Models for Artificial General Intelligence
- » Improving the Matrix Multiplication Exponent with Modern Optimization
- » How Far Are We From AGI: Are LLMs All We Need?
- » Dynamic Integration of Multimodal Entity Linking with LLM
- » Deep Linear Networks at Initialization
- » Qualifier-Aware Approximate Scientific Reasoning
- » Structure-Guided Evidence Packing for LLM Schema Matching
- » Enhancing Multimodal Entity Linking with Fine-Grained Attributes
- » Incremental Memory Activation for Long-Context Sequence Modeling
- » OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
- » Mathematics in the Age of AI
- » AI-redesigned starting points and outcomes enhance protein evolution
- » From Output-Sensitive Indexing to Partial-Order Motif Estimation
- » SIGMOD 2026: From Relational Databases to AI-Native Data Systems
- » A Structural Informatics Guide to Kinase Selectivity...
- » From Binary Interaction Fingerprints to a Multimodal Kinase Atlas
- » An Evidence-to-Prediction Stack for Kinase Drug Discovery
- » Boltz: From Physical Steering to Synthesis-Aware Molecular Design
- » Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
- » ASI-Bench: Measuring Scientific Autonomy Beyond Human Methodological Guidance
- » Training AI Scientists to Replicate Research
- » OpenDDE: From All-Atom Structural Reasoning to an Open Drug Discovery Engine
- » IsoDDE Trends: From Bigger Cofolding Models to Generalization-Aware Closed-Loop Drug Design
- » Intern-S2-Preview: Building a Scientific Agentic Foundation Model
- » RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
- » Rethinking Temporal Knowledge Graph Representation Learning: From Entities to Evolutionary Event-Centric Clusters
- » PRISM-DDE: Physics-Grounded and OOD-Robust Drug Design through Interventional Reasoning, Ensemble Sampling, and Multi-Objective Generation
- » IsoDDE: From Biomolecular Structure Prediction to a Computational Drug Design Engine
- » Improving Enzyme Prediction with Chemical Reaction Equations by Hypergraph-Enhanced Knowledge Graph Embeddings
- » Evo-Bench: Can Language Models Improve Agent Harness?
- » Designing and Evaluating an Agentic RAG System for a Domain-Specific Research Archive
- » PRISM-DDE: Physics-Grounded and OOD-Robust Drug Design
- » Where are data mining societies heading?
- » Frisch-Waugh-Lovell Theorem and Orthogonalization
- » 12 traits emotionally intelligent people share
- » How to get your ideas to spread
- » Boosting Relational Deep Learning with Pretrained Tabular Models
- » Deep Learning for Protein Engineering Primer
- » Language Modeling from Scratch
- » Distilling Foundation Models via Energy Hessians
- » Inference Scaling; A New Frontier for AI Capability
- » Mixed-modal Language Modeling
- » Reducing the Dimension of Language
- » 5 Unbelievably Useful AI Tools For Research in 2025
- » Why Intelligent People Scare Society
- » Google’s New AI Is Recreating the Whole World ...
- » Boltzmann Machines - Goeffrey Hinton
- » Accelerating Scientific Discovery with AI
- » How Deep Research Works
- » How to Live an Asymmetric Life
- » 4o Image Generation in ChatGPT and Sora
- » WTF is Artificial Intelligence Really?
- » Accelerating Scientific Discovery with AI
- » AI should NOT be regulated at all! - Domingos
- » Bayesians and Analogical Learning in AI
- » The Symbolist Approach to AI
- » Mathematical Obstacles on the Way to Human-Level AI
- » Inverse problems with experiment-guided AlphaFold
- » Why Can't AI Make Its Own Discoveries? — With Yann LeCun
- » How DeepSeek changes the LLM story
- » Why it Matters That Babies and Language Models are ...
- » Knowledge is structured and domain-specific
- » Rules vs. Neurons and what may be next
- » Why Physical AI Will Arrive Before AGI?
- » Neuroscience and AI; a symbiosis
- » Nvidia's GTC 2025 Keynote
- » How to Develop Teams of AI Agents with NVIDIA AgentIQ
- » François Chollet on OpenAI o-models and ARC
- » Cosmos World Foundation Model Explained
- » Huge Language Models and Neuro-Symbolic AI
- » Rethinking Recommender System's Sustainability
- » The Next Wave of AI - Physical AI
- » Causality for NLP Reading List
- » Group Relative Policy Optimization(GRPO)
- » Measuring Multimodal Reasoning with the MMMU Benchmarks
- » Generative Modeling
- » How Intelligent Systems Are Transforming Business
- » Can LLMs Achieve Casual Reasoning and Cooperation?
- » Father of AI - AI Needs PHYSICS to EVOLVE
- » Augmenting Causal Discovery with LLMs
- » Future of AI and Games
- » Weakly supervised causal representation learning
- » NVIDIA CEO Jensen Huang Keynote at CES 2025
- » Designing Advanced AI Agent Architectures for Intelligent Systems
- » Large Language Models in 2025
- » Knowledge Graph or Vector Database… Which is Better?
- » Fixing RAG with GraphRAG
- » Scaling AV Data With Omniverse and Cosmos
- » Build Custom World Foundation Models with NVIDIA Cosmos
- » Causality Upside Down
- » Intro to GraphRAG
- » Reproducibility Study of Explaining Temporal Graph Models
- » Weakly Supervised Causal Representation Learning
- » Neural Radiance Fields
- » What is DeepSeek? AI Model Basics Explained
- » Question Generation using Deep Learning in NLP
- » Causal Machine Learning in Python
- » R1, OpenAI’s o3, and the ARC-AGI Benchmark
- » Which Agentic AI Framework to Pick?
- » Time and Space in the Brain
- » Towards Human-like Educational Question Generation with LLMs
- » Chatbots vs AI Assistants - Key Differences
- » The Shape of AI to Come!
- » Cohort Construction and Refinement
- » A Path Towards Autonomous Machine Intelligence
- » What is Agentic RAG?
- » Implications of Artificial General Intelligence
- » Demystifying Long Chain-of-Thought Reasoning in LLMs
- » Potential Outcome Framework and Structured Causal Models
- » AI Trends for 2025
- » Non-linear Causal Discovery for Addtive Noise Models
- » Building Knowledge Graphs with LLM Graph Transformer
- » Financial Machine Learning - A Practitioner’s Perspective
- » Causal Hierarchy Theorem
- » Backdoor Criterion
- » Covariance-based Causal Discovery
- » Actual Causality - A Survey
- » Progress in Agentic AIs - Sakana AI
- » Interpretable Deep Learning for New Physics Discovery
- » Causal-aware Reasoning
- » When AI meets Computational Fluid Dynamics
- » Machine Learning on Function Spaces
- » Review - Symbolic Regression
- » OpenAI o1
- » Ontologies, Graph Deep Learning, & AI
- » Deep Symbolic Regression
- » Biophysics-Informed Neural Networks
- » Physics Informed Machine Learning through Symbolic Regression
- » Unlocking GenAI with GraphRAG & Knowledge Graphs
- » Step-by-step Code for Knowledge Graph Construction
- » Graph RAG - Improving RAG with Knowledge Graphs
- » How to Build Knowledge Graphs With LLMs
- » PINNs - Ordinary Differential Equations Tutorial
- » Scaling LLM Test-Time Compute
- » Introduction to Deep Research
- » PIML and Kolmogorov-Arnold Networks (KANs)
- » Symbolic Regression with Transformers
- » On Learning Heterogeneity and Non-Spuriousness in Causal Graphs
- » Physics-Informed Machine Learning for Engineering Applications
- » Large World Model for Large Context MultiModal LLM
- » Advances in Causal Representation Learning Discovery
- » Agentic AI - A Progression of Language Model Usage
- » Agents Thinking Fast and Slow - A Talker-Reasoner Architecture
- » Understanding Learning and Computation through Symmetry
- » Causal Representation Learning in the Context of Perturbation Screens
- » Unifying LLMs and Knowledge Graphs
- » Causal Discovery & Representation Learning
- » Bridging Machine Learning and Physics
- » A Connection between Probability, Physics and Neural Network
- » Causal Representation Learning - Advances and Perspective
- » Beyond Transformers - Intro to RWKV Architecture & The World To
- » Large Concept Models (LCMs)
- » RAG with a Neo4j Knowledge Graph
- » OpenAI o3, DeepSeek-V3, and the Brundage/Marcus AI bet
- » Learning operators using deep neural networks for multiphysics ...
- » 10 Things Coming In 2025 (A.I In 2025 Major Predictions)
- » Bayesian symbolic regression and the learnability
- » Deep End-to-End Causal Inference
- » Top Strategic Tech Trends for 2025
- » Open AI's Q* Is BACK! - Was AGI Just Solved?
- » Deep End-to-end Causal Inference
- » Physics of Intelligence for Trustworthy and Green AI
- » Can AI disover new physics?
- » LLMs for Causal Inference
- » Causal Representation Learning & Optimal Intervention
- » Decoding eCommerce- Why Causal AI adds unique value
- » Introduction To Causal Inference And Directed Acyclic Graphs
- » Physics-Informed Neural Networks and Verification
- » Physics-Informed Neural Networks - Limitations and Extensions
- » An Introduction to Causal AI
- » Evaluating RAG Performance with Vector Databases
- » Causal Representation Learning
- » XAI meets Natural Language Processing
- » The New Science of Cause and Effect
- » Microsoft GraphRAG - The Best RAG + KG Architecture
- » What is the BLEU metric?
- » Approximating functions, functionals and operators
- » From Large Language Models to Reasoning Language Models
- » Large Language Models and Causal AI
- » Reasoning Using Large Language Models
- » Towards reasoning in Large Language Models - A survey
- » Graph-of-Thoughts (GoT) for AI reasoning Agents
- » Causality - Counterfactuals
- » Building Causal AI Products for Effective Decision-Making
- » NVIDIA CEO Jensen Huang Keynote at CES 2025
- » Causal inference and LLMs; A New Frontier
- » Causality at the Intersection of Simulation, Inference, Science
- » Large language models (LLMs) and Causality
- » Introduction To The MITRE ATT&CK Framework
- » Causal Parrots; Large Language Models May Talk Causality
- » Causal Inference and Large Language Models
- » What's Next for AI in 2025? (Superintelligence Ahead)
- » OpenAI Just Revealed They ACHIEVED AGI (OpenAI o3 Explained)
- » How Do We Build a General Intelligence?
- » Artificial Super Intelligence Might be Here Already
- » Current State of AI Reasoning
- » Artificial General Intelligence (AGI)-Level Reasoning
- » Future of AI and Games
- » Forest-of-Thoughts; AI Test-Time Compute Reasoning
- » AGI Alignment Approaches
- » AGI Alignment Techniques
- » AGI Alignment - Ensuring AGI Meets Various Needs
- » The Future of AGI Systems
- » Cost and Efficiency
- » Inference Techniques
- » Decentralization, Training Dynamics and Scaling
- » Efficient Fine-tuning LLMs with PEFT and LoRA
- » Large-Scale Training
- » Beyound Transformers
- » Model Compression
- » Causal AI for Decision Making
- » Seminar with Professor Geoffrey Hinton
- » What is Causal AI?
- » Artificial General Intelligence (AGI) Levels
- » AI Interfaces to Digital World
- » AI-Level Metacognition
- » Expressive Power of Temporal Message Passing
- » RELBENCH; A Benchmark for Deep Learning on Relational Databases
- » A Benchmark for Learning on Temporal Knowledge Graphs
- » Sutras for Strategic Autonomy in AI
- » Ollama Course – Build AI Apps Locally
- » LangChain Tutorial
- » GraphRAG; LLM-Derived Knowledge Graphs for RAG
- » Hugging Face Course
- » Awesome AGI Survey
- » We’re Close to Artificial General Intelligence
- » The Man Who Predicted AGI Decades Ago
- » AI-Ready Data. What Does That Mean!?
- » How Far Are We From Achieving AGI?
- » 20 Emerging Technologies That Will Change The World
- » Artificial General Intelligence by 2030?
- » 8 Use Cases for Artificial General Intelligence
- » Training Exact Ambient Diffusion Models with Noisy Data
- » Visualizing transformers and attention
- » LangChain vs LangGraph; A Tale of Two Frameworks
- » Principles of Macroeconomics
- » Large Bipartite Subgraph
- » Dynamic Deep Learning
- » Towards Autonomous 6G Networks and the Role of Advanced ML
- » From Multimodal LLM to Human-level AI
- » 6G Networks - A New Era of AI and Machine Learning
- » Making Temporal Betweenness Computation Faster and Restless
- » Multimodal Machine Learning
- » A Brief Introduction to Causal Inference
- » Intro to Quantum Gibbs Samplers - Algorithmic Ingredients
- » Long Range Propagation on Continuous-Time Dynamic Graphs
- » Graph Neural Networks and Spectral Graph Theory
- » Maximum Entropy Method
- » What is Agentic AI?
- » Moravec's Paradox
- » Invariant Learning
- » How Could Machines Reach Human-Level Intelligence?
- » Bayesian Inference - Parametric Inference, Predictive Inference
- » Decoding on Graphs; Empower LLMs with KGs
- » Data Heterogeneity Analysis for Out-of-Distribution Generalization
- » Generative Retrieval
- » Change of Variable Rule
- » Chernoff and Hoeffding bounds
- » Spectral Graph Theory
- » Multimodal Large Language Models
- » RL Loses Against Multi-Agent Intelligence
- » DuckDB in the wild
- » How to transform tabular data into a graph
- » Isoperimetric Number
- » Converting a Tabular Dataset to a Graph Dataset for GNNs
- » Towards Neuro-Symbolic AI with Knowledge Graphs and LLMs
- » Toward Understanding In-context Learning
- » On large language models and transformers
- » Understanding and Improving Efficient Language Models
- » The Hierarchy of Needs for Training Dataset Development
- » Uplift Modeling; From Causal Inference to Personalizations
- » Unifying Graph Neural Networks
- » LLMOps and FMOps for e-commerce
- » What Are Drifts and How to Detect Them?
- » Deep Learning of Dynamics and Coordinates with SINDy Autoencoders
- » Introduction to Llama-agents Framework
- » Building Trusted AI with LLMs
- » How Domain-Specific AI Agents Will Shape the Industrial World
- » Harvard Presents NEW Knowledge-Graph AGENT (MedAI)
- » ParadeDB – Postgres for Search and Analytics
- » Re-thinking Transformers
- » XAI for LLMs; looking under the hood of Large Language Models
- » Physics-informed Machine Learning for Inverse Problems
- » Efficient Gaussian Splatting
- » Evaluating AI models for structure-based drug design
- » Discrete Flow Matching
- » Understanding Large Action Model (LAM)
- » How I Understand Flow Matching
- » Toward a better Deep Learning
- » Geometric Probabilistic Models
- » Fine-tuning and Merging LLMs
- » Normalizing Flows
- » Improving and Generalizing Flow-Based Generative Models
- » Flow Matching; Simplifying and Generalizing Diffusion Models
- » A Fast, Embeddable, Modular Analytic Query Engine
- » Improving equality and productivity with AI-driven tax policies
- » Scaling Limits of Neural Networks
- » Economic Policy Design using DRL and AI Simulations
- » AI Economist - How can AI FIX taxes?
- » Economics and Probabilistic Machine Learning
- » Rethinking Physics Informed Neural Networks
- » Differential Equations and Dynamical Systems
- » High Level Overview of AI and ML in Science and Engineering
- » A Trip Down the Generative Graphics Pipeline
- » Decoding Google Gemini with Jeff Dean
- » A Brief Introduction to Neural Radiance Fields
- » SGD and Weight Decay Secretly Compress Your Neural Network
- » Morris Approximate Counter
- » Towards Understanding the Implicit Regularization Effect of SGD
- » Language Models as World Models
- » Building LLMs from the Ground Up
- » Marginal-based Methods for Differentially Private Synthetic Data
- » Differentially Private Synthetic Data via Foundation Model APIs
- » GraphRAG; The Marriage of Knowledge Graphs and RAG
- » Decoding the Human Brain – A Neurosurgeon’s Experience
- » ML for High-Performance Climate and Earth Virtualization Engines
- » How To Read AI Research Papers Effectively
- » Building Large Language Models (LLMs)
- » DuckDB – Overview and latest developments
- » Unreasonably Effective AI with Demis Hassabis
- » The COMPLETE TRUTH About AI Agents
- » The Future of Knowledge Assistants
- » Responsible AI development
- » The Reparameterization Trick
- » How to Read Machine Learning Research Papers
- » A tutorial on on neurosymbolic techniques
- » Analysis by Synthesis
- » The tip and the iceberg; deep learning and embodiment
- » Generating Synthetic Tabular Data That’s Differentially Private
- » TableDiffusion; Generative AI for private tabular data
- » DeepJoin Joinable Table Discovery with Pretrained Language Models
- » Synthetic data generation with CTGAN
- » Retrieval and Re-Reranking
- » What Does Machine Learning Have to Offer Mathematics?
- » What do tech pioneers think about the AI revolution?
- » The Age of AI, Eric Schmidt
- » Decoding the Decoder LLM without de code
- » How to improve your writing
- » The Potential for AI in Science and Mathematics
- » Introduction to Self-Driving
- » Towards Foundation Models for Graphs
- » Energy Based Models
- » Awesome-Graph-LLM
- » Spark Tutorial For Beginners
- » Meta AI, Limits of LLMs, AGI & the Future of AI
- » Analyze Data with LLMs and Python
- » DuckDB Spatial; Supercharged Geospatial SQL
- » Robust Distortion-free Watermarks for Language Models
- » Space is a latent sequence; A theory of hippocampus and PFC
- » Privacy in Web Advertising - Analytics and Modeling
- » Mining Temporal Networks
- » Multimodal Pretraining and Generation for Recommendation
- » Text Attributed Graph Representation Learning
- » Curriculum Learning Theories, Approaches, Applications
- » Neural Contextual Bandits for Personalized Recommendation
- » Large Language Models for Recommendation
- » Data Drift, Quality, Bias and Explainability
- » Mining Exploratory Queries for Conversational Search
- » Recent Advances in Image Generative Foundation Models
- » Sublinear time algorithms in learning
- » A Bi-metric Framework for Fast Similarity Search
- » Vector Search and Embeddings in Organizations
- » Modality Alignment for Multimodal Perception
- » Multimodal Large Language Model Tutorial
- » Probability for Computer Scientists
- » AGI Levels by OpenAI, Grok 2 and Neuralink Update
- » Large Multimodal Models
- » Geometric Deep Learning; From Euclid to Drug Design
- » Algorithmic Discrepancy Theory and Randomized Controlled Trials
- » Continual Learning Beyond Catastrophic Forgetting
- » Project Kuiper; Fast, Affordable Broadband
- » AI for 5G Advanced Toward 6G
- » AI & Machine Learning for Satellite Communications with SES
- » AI for 3D Generation
- » AI for Content Creation
- » Make self-adjusting data structures concurrent
- » Privacy Preserving ML with Fully Homomorphic Encryption
- » Workshop on Urban Scene Modeling
- » KDB.AI | Introduction to Vector Search
- » Multimodal Learning on Graphs
- » From Multimodal LLM to Human level AI
- » Foundation Models for Autonomous Systems
- » Using LLM Agents with Llama 3, LangGraph and Milvus
- » Building Intelligent RAG Applications
- » Learn PostgreSQL fast! | PostgreSQL for beginners
- » The Influence of Computation on Inference
- » Machine learning models of differential gene expression
- » Recent Advances in Vision Foundation Models
- » Illuminating protein space with generative models
- » On the Generalization Capability of Temporal Graph Learning Algorithms
- » Spectral Graph Neural Networks
- » Audio-visual self-supervised baby learning
- » From Higher-Order Graph Structures to Link Prediction and Beyond
- » History and Future of AI at Data + AI Summit 2024
- » How Can Privacy Exist in a Data-Driven World?
- » Can Learned Indexes be Built Efficiently?
- » The Platonic Representation Hypothesis
- » programming ≠ coding
- » SIGMOD 2024 - Alibaba Cloud PolarDB-MP
- » Python RAG Tutorial with Local LLMs
- » Learn RAG From Scratch
- » PostgreSQL as a Vector Database
- » Kernels for Graphs
- » Milvus 101- Most Advanced Vector Database
- » Vector Similarity Search & Indexing Methods
- » Combine Your Data with LLMs with Advanced Search
- » Learn How to Build Multimodal Search and RAG
- » Many shades of Machine Learning Acceleration
- » Charm++ and Adaptive MPI
- » GenAI in Life Sciences Summit
- » Grounding for Gemini with Vertex AI Search and DIY RAG
- » HPC and AI/ML; A Synergistic Relationship
- » Multimodal Retrieval-Augmented Generation with Gemini
- » What is LangChain?
- » PyTorch on Apple Silicon
- » MLP vs KAN, Math, B-Splines, Universal Approximation Theorem
- » Kolmogorov-Arnold Networks VS Regular Deep Learning
- » Kolmogorov-Arnold Networks
- » A Causal Inference Framework for Combinatorial Interventions
- » Introducing GPT-4o with Large Language Models
- » Zero-Shot Relational Learning on Temporal Knowledge Graphs with LLMs
- » Continuous-time Graph Representation with Sequential Survival Process
- » Topological Representations for Temporal Graph Property Prediction
- » LangGraph 101; it's better than LangChain
- » Deep Learning Under Distribution Shift
- » Automating Enterprises With Foundation Models
- » Score Based Models
- » Quantum Computing in Practice
- » DRO and Its Applications in Communication and Networking
- » Data-driven and Distributionally Robust Optimization and Applications
- » Mathematical Foundations of Robust and DRO
- » Introduction to Distributionally Robust Optimization
- » Fundamentals of Intelligent Reflecting Surfaces
- » Multimodal language models for mapping the genotype-phenotype relationship
- » Vector Embeddings Tutorial
- » Vector Database 101 - A Crash Course
- » LLM and Vector Databases - Concepts, Architectures, and Examples
- » Vector Databases Explained
- » Vector Database Fundamentals
- » Indexing in Vector Databases
- » Complete Tutorial on Vector Database
- » Uncovering and Inducing Interpretable Causal Structure
- » GNNs in Computational Biology
- » EVO - DNA Foundation Models
- » Bayesian Causal Inference & Propensity Scores
- » Understanding Bayesian Statistics Without Frequentist Language
- » Prof. Chris Bishop's NEW Deep Learning Textbook!
- » Towards Conversational Diagnostic AI
- » Anomaly Detection in Continuous-Time Temporal Provenance Graphs
- » Gemini Full Breakdown + AlphaCode 2 Bombshell
- » Googles GEMINI Just SHOCKED The ENTIRE INDUSTRY!
- » Multimodal Prompting with a 44-minute Movie
- » Approximate Maximum Matching
- » Prompt Engineering, RAG, and Fine-tuning
- » Building Production-Ready RAG Applications
- » Entropy & Mutual Information in Machine Learning
- » Towards Federated Analytics with Local Differential Privacy
- » The Science of LLM Benchmarks - Methods, Metrics, and Meanings
- » Formal Methods and Machine Learning
- » Formal Methods and Deep Learning
- » HyperPCM-Robust Task-Conditioned Modeling of Drug-Target Interactions
- » Objective-Driven AI
- » Explainability of Graph Neural Networks
- » Why should you care about DuckDB?
- » Dynamic Graph Information Bottleneck
- » Diffusion Models on Sampling Rare Events
- » Deep Probabilistic Models with Tractable Inference
- » Nuggets of Shannon Information Theory
- » Large Language Models as Copilots for Theorem Proving
- » Application Development using Large Language Models
- » A New 3D Digital Human Creator For All!
- » 나의 문화유산답사기 30주년
- » The Fifth Paradigm of Scientific Discovery
- » Bringing analytical SQL directly to your Python shell
- » Decoding the Information Bottleneck in Self Supervised Learning
- » Information Bottleneck Theory of Deep Learning
- » MultiDiffusion; Fusing Diffusion Paths for Controlled Image Generation
- » In-Process Analytical Data Management with DuckDB
- » Generalization in diffusion models
- » Gemini Multimodal RAG Applications with LangChain
- » Exciting Trends in Machine Learning
- » How to Build a Metadata Driven Data Pipelines with Delta Live Tables
- » Learn How to Build Real-Time Warehouses on Lakehouse
- » Databricks Lakehouse Overview Training
- » Simplify ETL pipelines on the Databricks Lakehouse
- » Delta Live Tables A to Z; Best Practices for Modern Data
- » Building Reliable ETL Pipelines with Azure Databricks
- » Graph-based Virtual Sensing
- » Online A/B Testing of Real-Time Event Detection Systems
- » Machine Unlearning of Features and Labels
- » Machine Unlearning Papers
- » Ecommerce Marketing Analytics; Top 8 Metrics EXPLAINED
- » Differential Privacy and Machine Unlearning
- » Foundation Models on Consumer Devices
- » Lakehouse with Delta Lake Deep Dive Training
- » Large Language Models for Program Optimization
- » Multimodal Reasoning; PaLM-E & Gemini
- » Text2SQL; The Dream versus Reality
- » Data Lakehouse and Data Mesh—Two Sides of the Same Coin
- » Pathways Language Model and Model Scaling
- » The Information Bottleneck Approaches in Deep Neural Networks
- » On Mutual Information Estimation
- » A Deeper Understanding of Deep Learning
- » The Information Bottleneck Theory of Deep Learning
- » Information Theory of Deep Learning
- » DeepMind Gemini 1.5 - An AI That Remembers!
- » Graph Machine Learning for 2024
- » Unlock Data Insights Faster with AI-Generated Sample Data
- » Graph Dashboards With LLM Powered Natural Language Queries
- » Approximate Nearest Neighbor and Product Quantizer
- » Choosing the Right Embedding Model, Chunking Strategy, and More
- » Document Curation for Retrieval Augmented Generation
- » Data Federation with Unity Catalog
- » The Data Intelligence Platform
- » Cross-Platform Data Lineage with OpenLineage
- » Mitigating LLM Hallucinations
- » Towards Foundation Models for Knowledge Graph Reasoning
- » Unveiling the Power of Multimodal RAG for Images and Text
- » Image Similarity Search with Vector Databases
- » Building a Music Recommender with Vector Databases
- » Document Semantic Search with Vector Databases
- » Sentiment Analysis with Vector Databases
- » Overview of RAG Approaches with Vector Databases
- » Graph-Based Approximate Nearest Neighbors (ANN) and HNSW
- » Enhancing Vector Database Queries with Metadata Filtering
- » Guiding Graph Embeddings using Path-Ranking Methods
- » Evaluating RAG Performance with Vector Databases
- » Chunking Best Practices for RAG Applications
- » Product quantization in Faiss and from scratch
- » Ambient Computing, Multimodal AI & Edge Computing
- » Composite AI, the Future of Computing and Human Capital
- » From Delta Sharing to Clean Rooms
- » What is a vector database?
- » Advanced RAG; Chunking, Embeddings, and Vector Databases
- » Unity Catalog Overview
- » How to Build LLMs on Your Company’s Data While on a Budget
- » A Technical Deep Dive into Unity Catalog's Practitioner Playbook
- » Which is the most reliable estimate?
- » Building an LLMOps Stack for Large Language Models
- » Introduction to large language models
- » Cost Optimization use cases with a Data Catalog
- » 5 Explosive Digital Marketing Strategies
- » Introduction to Vector Search
- » Atlan AI for Documentation -- LIVE Demo
- » LLMOps; Everything You Need to Know to Manage LLMs
- » How to Train Your Own Large Language Models
- » The future of generative AI
- » Reset KOREA!, The 1st Seminar
- » Intro to Large Language Models
- » Metadata Use Cases Demo in Atlan
- » The Anatomy of an Active Metadata Platform
- » 3 Keys for Collective Intelligence
- » Towards Self-Service Analytics
- » Self-designing Data Systems for the AI Era
- » Active Metadata Management
- » Active Metadata with Data Quality
- » The Next Generation of Active Metadata Platforms
- » Knowledge Graph Reasoning with Graph Neural Networks
- » The Modern Metadata Platform
- » Metadata Management & Data Catalog
- » Temporal Graph Benchmark for Machine Learning on Temporal Graphs
- » Safely Using Gen AI With Active Metadata and Data Fabric
- » A General Graph Neural Network Framework for Link Prediction
- » Neural Bellman-Ford Networks
- » Towards Interpretable Data Science
- » Differential Privacy And The Complexity Of Simple Queries
- » Privacy Preserving AI
- » The Promise of Differential Privacy
- » A Survey on Graph Neural Networks for Time Series
- » Towards Foundation Models for Knowledge Graph Reasoning
- » Stylish Hierarchical Navigable Small World Indexes
- » Retrieval-Augmented Language Model Pre-Training
- » Domain Knowledge Augmented AI for Databases
- » AND/OR Search Spaces for Anytime Probabilistic Reasoning
- » Generative AI And Programming
- » Gartner's Top 10 Tech Trends for 2024
- » Making Retrieval Augmented Generation Better
- » Emerging architectures for LLM applications
- » Tree of Thought Prompting
- » Building a managed database service with Kubernetes Operators
- » A Purpose-Built Vector Data Management System
- » Best Practices for Query Performance Testing
- » OpenAI Embeddings and Vector Databases Crash Course
- » Long-Range Genomic Sequence Modeling
- » How to Choose a Vector Database
- » Awesome Vector Database
- » Vector Databases simply explained! (Embeddings & Indexes)
- » OpenAI DevDay, Opening Keynote
- » Knowledge Distillation
- » Vector Database for Large Language Models in Production
- » Embeddings, Vector Databases, and Search
- » Fast, Approximate Vector Queries on Very Large Unstructured Datasets
- » How I make beautiful GRAPHS and PLOTS using LaTeX
- » Transformers for Multimodal Self Supervised Learning
- » Lance; A Modern Columnar Data Format
- » Feature Store Architectures & Technical Challenges
- » Machine Learning for Multi-Scale Molecular Simulation and Design
- » Reasoning Algorithmically; from Toy Experiments to AGI Modules
- » Table Representation Learning
- » Language Models and Applications in Data Management
- » Categories for AI 1; Why Category Theory?
- » Estimating Separable Matching Models
- » Action Matching; Learning Stochastic Dynamics from Samples
- » Categories, Graphs, Reasoning
- » Heterogeneous Continual Learning
- » Tractable Control for Autoregressive Language Generation
- » Approximating the TV Distance Between Two Product Distributions
- » The Rise of Tractable Circuits
- » Tractable Bounding of Counterfactual Queries
- » A Tutorial on Causal Representation Learning
- » Explainable Data Drift for NLP
- » Open-Source Spotlight - Deepchecks
- » Develop test suites for machine learning models and data
- » Kolmogorov-Smirnov Test Explained
- » L-Infinity Distance Explained
- » Wasserstein Distance Explained
- » Jensen-Shannon Distance Explained
- » Comparison of Data Drift Detection Methods
- » Sketching and Projecting
- » Randomized Embeddings and Neural Networks
- » Memory-Regret Tradeoff for Online Learning
- » Sketching Techniques for Kernel Density Estimation
- » Fast Attention Requires Bounded Entries
- » From Machine Learning to Autonomous Intelligence
- » Less is More with PostgresML
- » The Power of Graph Learning
- » AI-Powered Database Optimization as a Service
- » Open Source Vector Search Engine and Vector Database
- » How to evaluate and explore data drift in ML systems
- » Hugging Face Tutorial
- » Python and PyTorch Tutorial
- » Data Drift & Model Drift Detection Using Python
- » Easiest way to Detect Data Drift Using Evidently
- » Data Drift Monitoring in Azure ML
- » Drifting Away; Testing ML Models in Production
- » Multimodal Deep Learning
- » Automating Model Monitoring and Drift Detection
- » Monitoring Model Quality in Streaming Machine Learning Applications
- » ML Drift; Identifying Issues Before You Have a Problem
- » Dynamic Graph Algorithms; What We Know and What We Don’t
- » How to Understand Clearly
- » Gentle Introduction to Causal Inference
- » Awesome Incremental Learning / Lifelong learning
- » Temporal Distributional Shifts
- » A Brief Introduction to Causal Inference
- » Explainable Deep Learning for Structured Data
- » Leveraging Privacy-Enhancing Technologies with LLMs
- » Probabilistic and Logical Circuits for Tractable Causal Reasoning
- » Probabilistic Reasoning and Learning for Trustworthy AI
- » Learned Query Optimiser At the Forefront of AI Driven Databases
- » Internals of Permissioned Blockchains
- » On the Role of Neural Collapse in Few-Shot Transfer Learning
- » Introduction to Data Structures and Optimization for Fast Algorithms
- » Attention Approximates Sparse Distributed Memory
- » Fine-Grained Complexity for Dynamic Graph Problems
- » Sketching
- » Graph Data Structures
- » Graph Linear Algebra
- » Kubeflow vs MLFlow
- » Language Models as Statisticians, and as Adapted Organisms
- » Differentially Private Sampling from Distributions
- » HNSW for Vector Search Explained and Implemented with Faiss
- » Incremental View Maintenance
- » Preserving Data Privacy in Federated Learning
- » On Localization in Language Models
- » Meaning in the age of large language models
- » Large Language Models Meet Copyright Law
- » Logic and Probabilistic Circuits
- » Prompt Engineering
- » Statistical Learning Theory and Neural Networks
- » LangChain "Advanced Retrieval" Webinar
- » Challenges and Opportunities in Differentially Private Federated Learning
- » LlamaIndex Overview & Use cases
- » In-Context Learning
- » 9 tips to help you PROVE MATH THEOREMS
- » Are LLMs the Beginning or End of NLP?
- » Bayesian Principles for Machine Learning
- » How to Speak
- » Differentially Private GNNs with Aggregation Perturbation
- » Recent Advances in Causality-based Recommendation
- » Interpretability via Symbolic Distillation
- » Synthesizing Relational Data with Differential Privacy
- » PrivSyn - Differentially Private Data Synthesis
- » Basics of Neurosymbolic Architectures
- » The Theory and Practice of Differential Privacy
- » Towards Reliable Use of Large Language Models
- » Cartel Screening and Machine Learning
- » Local Differential Privacy in Practice
- » Survey on Privacy/Security in FL
- » NVIDIA Keynote at SIGGRAPH 2023
- » Trustworthy AI - A Computational Perspective
- » High-Dimensional Bayesian Optimization
- » Self-Supervised Learning in Recommendation
- » Keeping AI under control through mechanistic interpretability
- » Towards Machines that can Learn, Reason, and Plan
- » Diffusion and Score-Based Generative Models
- » Differentially Private Diffusion Models
- » Foundation Models and Fair Use
- » Spatial Data Science Methods for Improving Models
- » Predictive Whittle Networks for Time Series
- » There's no such thing as MIRACLE
- » Locally Private Graph Neural Network
- » What is a Vector Database?
- » A New Upper Bound for the Heilbronn Triangle Problem
- » AI and the Future of Humanity
- » Two Paths to Intelligence
- » Large Multimodal Models
- » ChatGPT for Data Analysts
- » Visual Prompting Livestream With Andrew Ng
- » Quantifying and Understanding Memorization in Deep Neural Networks
- » Converging Advances to Accelerate Molecular Simulation
- » Learning Delaunay Surface Elements for Mesh Reconstruction
- » Knowledge Graphs Seminar
- » Data Cataloging with Knowledge Graphs
- » The Foundation of a Data Fabric
- » Data Mesh, Data Fabric, Data Lakehouse
- » Tractable Probabilistic Circuits
- » Distributed Analytical Database Systems
- » GraphZeppelin - Streaming Graph Connectivity at Scale
- » Understanding Graph Data Representations in Triplestores
- » Graph-Powered Data Exploration
- » Google BigQuery
- » Conformal Prediction Tutorial
- » Traffic Prediction Paper Collection
- » End-to-end Optimization of Machine Learning Prediction Queries
- » Compute Complex Temporal Join Queries Efficiently
- » Making Learned Query Optimization Practical
- » Universal Database Optimizer
- » Machine Learning for Query Optimization
- » ML Explainability
- » Towards Generalizable Autonomy
- » Building an AI and ML ready Modern Data Platform
- » Diffusion Probabilistic Modelling of Protein Backbones in 3D
- » ICCV Authors Guidelines
- » Diffusion Probabilistic Models
- » Stable Diffusion - What, Why, How?
- » Deep Energy-Based Learning
- » Incident Prediction in Spatio-Temporal Road Graph Networks
- » Diffusion probabilistic modelling of protein backbones in 3D
- » Contrastive Learning in PyTorch
- » Neural Rendering
- » Anatomy of a Research Paper
- » Geometric Deep Learning for Drug Discovery
- » Deploy Custom Python Model Server
- » Contrastive Learning in PyTorch
- » InferenceService using a Custom Torchserve Image
- » From Machine Learning to Autonomous Intelligence
- » Towards a Learned Index Structure for ANN Search
- » Graph Processing; from Academic Research to Industrial Application
- » Katana Graph; A Graph Intelligence Platform
- » Machine Learning for Scientific Discovery
- » Graph Neural Networks as Gradient Flows
- » Ab-Initio Potential Energy Surfaces
- » Reinforcement Learning via Sequence Modeling
- » Recipe for a General, Powerful, Scalable Graph Transformer
- » Spatial Hash Grids & Tales from Game Development
- » Cardinality Estimation Benchmark
- » Spatial Indexing in PostGIS
- » Data-driven Learned Metric Index; an Unsupervised Approach
- » Synopses - Samples, Histogram, Wavelets and Sketches
- » Query Execution in MonetDB
- » Low overhead self-optimizing storage for compression
- » A Database Tuning Tool that "Reads the Manual"
- » Rethinking Graph Transformers with Spectral Attention
- » Introduction to TorchServe
- » MicroK8s Installation & Simple Commands
- » Diffusion Models from Scratch in PyTorch
- » Deep Learning Theory Lectures
- » Kubeflow Fairing
- » Kubeflow Fairing, Pipelines, and Training
- » On Recoverability of Graph Neural Network Representation
- » Deploy Model to KServe
- » TorchScript and PyTorch JIT
- » Spectra of Graphs and Hypergraphs
- » How to Serve PyTorch Models with TorchServe
- » A Novel Data Set for Information Retrieval on the Basis of Subgraph Matching
- » Graph Embedding in Vector Spaces Using Matching-Graphs
- » Google Cloud BigQuery ML Using SQL
- » Open World Lifelong Learning
- » On Machines that can Learn Continually
- » Introduction to Continual Learning
- » Introducing OpenAPI Generator
- » Kubeflow Development Environment
- » KFServing Deep Dive
- » Protein structure prediction with AlphaFold
- » Deep Learning for Scientific Computation
- » Started with AI in Drug Discovery
- » Istio Simplified
- » Knative and Microk8s with Multipass
- » KServe in Kubenetes
- » Graph Ordering Attention Networks
- » Introduction to KServe
- » Position-Aware Graph Neural Network using Reachability Estimations
- » Isomorphism Using Adjacency Matrix
- » Efficient Probabilistic Truss Indexing on Uncertain Graphs
- » Toward Verified Artificial Intelligence
- » Modern Data Stack
- » PyTorchJobClient
- » KServe (Kubeflow KFServing) Live Coding Session
- » Workflow for ML Projects — MLOps
- » Kubeflow Setup
- » Introduction to Data Mesh
- » Theory of Graph Neural Networks
- » Representational Power of Graph Nerual Networks
- » Task structure and generalization in graph neural networks
- » Geometry Processing with Neural Fields
- » Trends in AI
- » RelationalAI Knowledge Graph Management System
- » Topological Graph Neural Networks
- » Causality and (Graph) Neural Networks
- » Using Graph Neural Networks for Multi-Node Representation Learning
- » Epistemic Uncertainty Estimation for Efficient Search of Drug Candidates
- » Toward Neuro Causality
- » Connect to MySQL Database from Visual Studio Code
- » Data-Efficient Graph Grammar Learning for Molecular Generation
- » Rethinking Graph Transformers with Spectral Attention
- » How GNNs and Symmetries can help to solve PDEs
- » Neural diffusion PDEs, differential geometry, and graph neural networks
- » BigQuery ML; Machine Learning with Standard SQL
- » GNN with Learnable Structural and Positional Presentations
- » Istio Service Mesh 101
- » Graph Neural Networks and Diffusion PDEs
- » Recommender Systems using Graph Neural Networks
- » Manage Multi-tenant ML Workloads Using Istio
- » Graph Neural Networks as Neural Diffusion PDEs
- » Exploring ML Model Serving with KServe
- » Kubeflow Tutorial | Model Serving
- » Using AI to accelerate scientific discovery
- » Java to MySQL using Visual Studio Code
- » Developing the Kubernetes Python Client
- » Kubernetes Patterns
- » Using Visual Studio Code for Java Maven Project
- » Mapping External Services
- » MiniKF; Kubeflow on your laptop
- » Gateway Routing Pattern
- » Kubeflow v1.5 Release Overview
- » TensorFlow Distributed Training on Kubeflow
- » Sidecar Pattern
- » YAML
- » Kubeflow on macOS
- » Why is Kubernetes called K8s?
- » Kubernetes Crash Course for Absolute Beginners
- » Marrying Top k with Skyline Queries
- » Spatial Skyline Queries on Triangulated Irregular Networks
- » Challenges and Solutions of Using Kubernetes for Blockchain Applications
- » PyTorch Training (PyTorchJob)
- » Kubeflow Architecture
- » Istio and Service Mesh
- » Kubernetes Tutorial for Beginners
- » Serving Machine Learning Models at Scale Using KServe
- » Advanced Model Inferencing Leveraging Kubeflow Serving
- » PyTorch via SQL Commands
- » Scaling Shortest Path Graph Queries on Very Large Networks
- » Hierarchical Core Maintenance on Large Dynamic Graphs
- » Shortest Paths and Centrality in Uncertain Networks
- » Bag of Tricks for Node Classification with Graph Neural Networks
- » The Case for Learned Index Structures
- » Deep Learning for Graph Similarity Search
- » HyperSPNs; Compact and Expressive Probabilistic Circuits
- » Learned Index Structures for Dynamic and Multi-Dimensional Data
- » Blame the Data, Not the System
- » Hyperbolic Embeddings in Machine Learning and Deep Learning
- » What are Temporal Databases?
- » Git Commit Message Style Guide
- » What is PrestoDB?
- » Spatial, High Dimensional, Temporal Data Indexing and Querying
- » A Learned Spatial Index for Range and kNN Queries
- » An Introduction to Spatial Data and its Applications
- » Robustness/Interpretability in Vision & Language Models
- » Visual Data Analysis; How? When? Why?
- » SageDB; A Self-Assembling Database System
- » Towards Zero-Shot Learning for Databases
- » From Workload-Driven to Zero-Shot Learning
- » From Notebook to Kubeflow Pipelines to KFServing
- » Improving Transfer and Robustness of Supervised Contrastive Learning
- » Approximate Query Processing
- » What are Probabilistic Data Structures?
- » Approximation Algorithms for Large Scale Data Analysis
- » Modeling Relational Data with Graph Convolution Network
- » Open-source Change Data Capture With Debezium
- » Finding Approximately Repeated Patterns in Time Series
- » Looper; An End-to-End ML Platform for Product Decisions
- » Learned Indexing and Sampling for Improving Query Performance
- » Principles of Good Machine Learning Systems Design
- » Deep Learning Design Patterns
- » Tips for Thinking Like a Machine Learning Architect
- » Machine Learning Design Patterns
- » Introduction to Kubeflow
- » Martingale Theory
- » Making Architecture Matter
- » Bayesian Inference for Big Data
- » Architecture and Cardinality Estimations for Graph Queries
- » What causes congestion?
- » Optimization problems in graphs with locational uncertainty
- » Deep Implicit Layers
- » Convex Functions
- » Quantum Deep Learning
- » Uncertainty and Out-of-Distribution Robustness in Deep Learning
- » Probabilistic Methods for Increased Robustness in Machine Learning
- » Probabilistic Circuits - Representations, Inference, Learning and Theory
- » FLAT-Fast, Lightweight and Accurate Method for Cardinality Estimation
- » Learned Query Scheduling
- » A 10 Minute Introduction to Kubeflow
- » Ethics of Artificial Intelligence
- » What is AI Ethics?
- » What is the Cardinality Estimator?
- » Qd-tree - Learning Data Layouts for Big Data Analytics
- » Sum-Product Networks
- » Towards Zero-Shot Learning for Databases
- » Machine Learning Design Patterns
- » Learned DBMS Components 2.0
- » Deep Multi-task and Meta Learning
- » Machine Learning Design Patterns - Rebalancing
- » Calcite Tutorial
- » NeuroCard - One Cardinality Estimator for All Tables
- » GNN based Recommender Systems
- » On the Nature of Data Science
- » Breaking the Limit of Graph Neural Networks using Local Mixing Patterns
- » Performance Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks
- » Data Fabrics for Enterprise Data Management?
- » Query Optimization and Acceleration at Dremio
- » AI4DB & DB4AI-Papers
- » Permissioned Blockchains
- » Apache Spark, Data Science + Machine Learning
- » Introduction to Temporal Graph Neural Networks
- » Traffic Forecasting with Pytorch Geometric Temporal
- » Geometric Deep Learning
- » What Is NFT? - Non Fungible Token
- » Deep Recommender Systems
- » Weisfeiler and Lehman Go Cellular; CW Networks
- » Matrix Multiplication, and the Asymptotic Spectrum Of Tensors
- » Traffic Prediction for Intelligent Transport System
- » Revisiting Knowledge Graph Completion From a Practical Perspective
- » Applying Machine Learning-based Database Tuning in Production
- » Cloud-Native Ledger Graph Database
- » A Probabilistic Model for Joint Inference from Differential Equations
- » Optimization Frameworks for Graph Clustering
- » Neuralising a Computer Scientist
- » Preparing For Your Dissertation Defense
- » Oral Dissertation Defense Preparation
- » How To Defend Your Thesis? Top 10 Tips For Success
- » How to Get a PhD in Computer Science
- » 100 Thesis Defense Questions in 3 Categories
- » 10 Mistakes to Avoid When Defending Your Thesis
- » How to prepare for your PhD thesis defence
- » Geometric Deep Learning-Past, Present, And Future Optimization
- » Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
- » How to write a literature review - my simple 5 step process!
- » Geometric Deep Learning - from Euclid to drug design
- » Graph Isomorphism in Quasipolynomial Time
- » Geometric Deep Learning Blueprint
- » Geometric Deep Learning-The Erlangen Programme of ML
- » KDD Cup OGB Large-Scale Challenge
- » Theoretical Foundations of Data-Driven Algorithm Design
- » Relational Inductive Biases, Deep Learning, and Graph Networks
- » The Future Is Big Graphs
- » The Universal Approximation Theorem
- » Equivariant Networks and Natural Graph Networks
- » An Introduction to Hamiltonian Monte Carlo Method for Sampling
- » Recurrent Neural Networks for Cognitive Neuroscience
- » Permutation Equivariance of Graph Filters
- » Graph Convolutional and Isomorphism Networks
- » Combinatorial Properties of the Weisfeiler-Leman Algorithm
- » Advances in Self-Supervised Learning
- » Contrastive Loss, Deep Metric Learning
- » Self-Supervised Learning
- » Contrastive Learning; A General Self-supervised Learning Approach
- » Supervised Contrastive Learning
- » What is Noise-Contrastive Estimation?
- » GNNs with Learnable Structural and Positional Representation
- » Knowledge Graph Representation
- » Temporal Graph Networks (TGN)
- » Building a Recommender System using Graph Neural Networks
- » Junction Tree Variational Autoencoder for Molecular Graph Generation
- » Understanding Graph Attention Networks
- » GVAE Training and Adjacency Reconstruction
- » Graph Representation Learning for Drug Discovery
- » Graph Neural Networks for Traffic Prediction
- » Visual Exploration of Trajectory Data
- » GPS Data Analysis with Python
- » 22 Python libraries for Geospatial Data Analysis
- » Clustering Trajectories
- » Towards Causal Representation Learning
- » Random Sum Product Networks
- » Understanding & Generating Source Code with Graph Neural Networks
- » Sum-Product Networks; The Next Generation of Deep Models
- » Deep Learning to Discover Coordinates for Dynamics
- » The Power of Graph Signal Processing
- » Some Mathematical Problems in Graph Signal Processing
- » On Laplacian Eigenmaps for Dimensionality Reduction
- » Overview of Graph Embeddings
- » Sum-Product Networks; Powerful Models with Tractable Inference
- » Sum-Product Networks
- » Geometric Deep Learning and Reinforcement Learning
- » Discovering Genetic Medicines with our AI Drug Discovery Platform
- » Proof of Euler's Formula
- » GNNs and RL in Traffic Optimization in Cities
- » Graph Neural Networks and Applications to Deep Reinforcement Learning
- » Writing Scientific Papers
- » Drug Discovery with GANs
- » PyTorch nn.Embedding()
- » Reproducing Kernel Hilbert Spaces
- » Dynamical Systems and Machine Learning
- » An Introduction to Hilbert Spaces
- » Graph Neural Networks in Computational Biology
- » What is Euler's Number 'e'?
- » Euler's Formula
- » The Characteristic Equation and Eigenvalues
- » Spanning Trees and Kirchhoff's Theorem
- » Acceptance Rate of AI Conferences
- » Deep Graph Learning Foundations, Advances and Applications
- » Learning Graphs from Data; A Signal Processing Perspective
- » Making Graphs Compact by Lossless Contraction
- » A Short Course in Spectral Graph Theory
- » An Introduction to Spectral Graph Theory
- » Spectral Graph Theory; Enter Linear Algebra
- » Spectral Graph Theory; The Standard Random Walk
- » Spectral Graph Theory; The Quadratic Form
- » The Laplacian Matrices of Graphs; Algorithms and Applications
- » Pragmatic Ridge Spectral Sparsification for Large-Scale Graph Learning
- » Knowledge Graph Embeddings Tutorial; From Theory to Practice
- » How to use edge features in Graph Neural Networks
- » Graph Representation Learning
- » Papers on Graph Neural Networks
- » A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation
- » Super-Constant-Pass Streaming Lower Bounds for Reachability
- » Awesone Neural ODE
- » Neural Differential Equations
- » Generative Adversarial Networks and TF-GAN
- » Fairness and Bias in Algorithmic Decision-Making
- » A Learned Sketch for Subgraph Counting
- » Learning over sets, subgraphs, and streams
- » Categorical Reparameterization with Gumbel-Softmax
- » A Deterministic Parallel APSP Algorithm and its Applications
- » How Do You Generate Synthetic Data?
- » Synthetic Tabular Data Generation
- » Decremental All-Pairs Shortest Paths in Deterministic Near-Linear Time
- » Streaming Lower Bounds for Reachability
- » Learning Deep Matrix Factorizations Via Gradient Descent
- » NVIDIA Omniverse and a Future of Shared Worlds
- » Introduction to Graph Neural Networks
- » CVPR 2021 Workshop on Autonomous Vehicles
- » Pytorch-BigGraph: A Large Scale Graph Embedding System
- » Unsupervised Intelligent Agents
- » Uncertainty, causality and generalization
- » Illustrated Guide to RNN, LSTM, and Transformers
- » Banach Space Representer Theorems for Neural Networks
- » Next-Generation Recurrent Network Models
- » Graph Representation Learning for Drug Discovery
- » PostgreSQL Optimizer Methodology
- » PPRGo-Scaling Graph Neural Networks with Approximate PageRank
- » The Energy-Based Learning Model
- » But how does bitcoin actually work?
- » Explainable AI Cheat Sheet - Five Key Categories
- » Digital Twins and Geospatial Data
- » Trends in Traffic Prediction
- » Understanding Competencies
- » Scaling Up Graph Neural Networks to Large Graphs
- » Inductive Logic Programming
- » Useful Resources for Traffic Prediction
- » A Video Game That Looks Like Reality!
- » Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
- » New lower and upper bounds for quantile summary algorithms
- » Data Summarization for Machine Learning
- » Position aware Graph Neural Networks
- » Instacart Data Description
- » Fast Counts on Big Data Systems
- » MonetDB; Scale Up Before You Scale Out
- » Kronecker Graphs, Data Generation, and Performance
- » AI+VR; The Kayfabe Life
- » Efficient Query Processing Using Machine Learning
- » How to use mathcha math online editor
- » Uncertainty estimation in supervised learning
- » Approximately Bayesian Ensembling
- » Efficient Data Processing on Modern Hardware
- » AI Bias and Fairness
- » Generative Models for Graphs
- » Evidential Deep Learning and Uncertainty
- » Learned Approximate Query Processing
- » Meta Learning Tutorial
- » Deep Learning Outline
- » Transfer Learning
- » Approximate nearest neighbor search in high dimensions
- » Learning-Based Sketching Algorithms
- » Deep Learning Under Distribution Shift
- » Principles for Tackling Distribution Shift
- » Scalable Graph Neural Networks with Deep Graph Library
- » Deep InfoMax
- » Introduction to Bandits in Recommender Systems
- » Our paper has been published in IEEE Access!
- » Constant Girth Approximation for Directed Graphs in Subquadratic Time
- » Conditionally optimal approximation algorithms
- » Sparsification of Graphs and Matrices
- » How to Write a Great Research Paper
- » Vision Transformer - Keras Code Examples
- » Vision Transformer
- » MLP-Mixer; An all-MLP Architecture for Vision
- » From AlphaGo to MuZero
- » Moral Machines; How culture changes values?
- » Generative Adversarial Networks
- » Hardness of Approximation Between P and NP
- » GPT-3 = Generation Pre-trained Transformer 3
- » Graph Attention Networks Implementation
- » Introduction to Pytorch Geometric
- » Deep Learning for Graphs
- » Geometric Deep Learning
- » Graph Neural Networks - Models and Applications
- » Matching of Matching Graphs
- » Graph Classification using Structural Attention
- » Approximate Personalized PageRank on Dynamic Graphs
- » GCNs for Web-Scale Recommender Systems
- » Inductive Representation Learning on Large Graphs
- » Write Research Paper Outline
- » How to Respond to Reviewer Comments
- » Limitations of Graph Neural Networks
- » Choice of Graph Representation
- » Inductive Representation Learning on Temporal Graphs
- » Applications of Graph ML
- » Machine Learning with Graphs
- » How to Review a Research Paper
- » Approximate standing queries on Stream Processing
- » Learning Mesh-Based Simulation with Graph Networks
- » Temporal Graph Networks for Deep Learning on Dynamic Graphs
- » Graph Neural Networks and Knowledge Graph Completion
- » Parallel and Distributed Computing in Python with Dask
- » Reducing Communication in Graph Neural Network Training
- » Mathematical Foundations of the GraphBLAS and Big Data
- » Graph Signal Processing - Accounting for Geometry in Data
- » Graph Signal Processing for Machine Learning Applications
- » Papers on Recommendation Systems
- » Representational Power of Graph Neural Networks
- » Tunable Stream Graph Embeddings at Scale
- » Graph Neural Networks
- » Graph Convolutional Networks using only NumPy
- » Temporal Graph Networks for Dynamic Graphs
- » Graph Algorithms as Matrix Vector Products
- » Distributed Machine Learning with Python
- » Deep Networks Are Kernel Machines
- » How the Quest for the Ultimate Learning Machine Will Remake Our World
- » Fast Distributed Algorithms for Girth, Cycles and Small Subgraphs
- » Graph Sketching, Streaming, and Sampling
- » Theoretical Foundations of Graph Neural Networks
- » Efficiently Answering Span Reachability Queries
- » Probabilistic Reachability for MDPs
- » How computer science can help fight COVID-19
- » Enable Digital Transformation with Big Spatial Data & Analytics
- » Online Approximation Techniques for Spatial Data
- » Sparse Matrices Beyond Solvers
- » Research Resources for Approximate Query Processing
- » Research Directions for Sketching Algorithms
- » The Forward-Backward Embedding of Directed Graphs
- » The Dynamics of Active Sensing in Social Networks
- » Large-scale Graph Representation Learning
- » Graph Embedding
- » Individual and Collective Graph Mining
- » New Machine Learning Tool Tracks Urban Traffic Congestion
- » Network Analysis
- » Getting Started With Network Datasets
- » Bourgain's Embedding
- » High Accuracy Protein Structure Prediction Using Deep Learning
- » Testing Correlation of Unlabeled Random Graphs
- » Designing Effective Scientific Presentations
- » Quick & Simple Call Graphs in Python
- » Latent Network Summarization
- » Asymptotic Spectral Distributions for Strongly Regular Graphs
- » Graph Convolutional Neural Networks for Molecule Generation
- » Deep Learning on Graphs
- » Principles and Applications of Relational Inductive Biases
- » Traffic Prediction with Advanced Graph Neural Networks
- » Papers on Graph Neural Networks
- » Self-Driving Databases
- » Network Representation Learning
- » Non-Volatile Memory for Database Management Systems
- » Related Papers on Graph Neural Networks
- » Finding a New Knowledge
- » Beautiful Elastic Simulations, Now Much Faster!
- » Approximate Nearest Neighbor Search in High Dimensions
- » Billion-scale Approximate Nearest Neighbor Search
- » Spatio-Temporal Traffic Prediction Using Deep Learning
- » Machine Learning Dissertations
- » Research Day
- » CS Theory Toolkit
- » Deep Learning with PyTorch
- » Graph Signal Processing
- » Deep Learning Lectures
- » Convolutional LSTMs for Video Prediction
- » Research Proposal
- » Nonlinear Dimensionality Reduction
- » What Data Platforms Can Do for Machine Learning Workloads
- » AI for Neuroscience and Neuroscience for AI
- » Optimal Join Algorithms meet Top-k
- » Machine Learning Projects Against COVID-19
- » Antistrong Digraphs
- » Reflections from the Turing Award Winners
- » Recent Progress in High-Dimensional Learning
- » Dynamics of Real Networks - Patterns and Algorithms
- » Chasing the COVID-19 Pandemic through Modeling
- » This AI Removes Shadows From Your Photos!
- » Deep Generative Models for Brain Reading
- » Setting Up Your Kubeflow ML Environment
- » Statistical Learning Theory for Modern Machine Learning
- » Deep Learning for Computer Vision
- » Big Ideas in Causality and Machine Learning
- » AI for physics & physics for AI
- » A Blueprint of Standardized and Composable Machine Learning
- » Random Walks on Directed Graphs
- » Neural Ordinary Differential Equations
- » A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
- » Variational Graph Recurrent Neural Networks
- » Influence Analytics in Graphs
- » Learning from Limited Labeled Data
- » State of the Industry of Machine Learning Platforms
- » Fundamentals of NumPy
- » Fundamentals of PyTorch
- » Towards Lifelong Learning Machines (L2L)
- » Graph Attention Networks
- » Learning Equivariant and Hybrid Message Passing on Graphs
- » Adversarial Examples and Human-ML Alignment
- » Graph Nets; The Next Generation
- » Meta-learning
- » Meta-learning of Optimizers and Update Rules
- » Efficient Deep Learning with Humans in the Loop
- » Generalizable Autonomy for Robot Manipulation
- » Conditional Channel Gated Networks for Task-Aware Continual Learning
- » Transfer/Low-Shot/Semi/Unsupervised Learning
- » Mathematical Modeling of Epidemics
- » How Behavior Spreads
- » Network Diffusion & Contagion
- » Explainable AI - Methods, Applications & Recent Developments
- » Graph Representation Learning
- » The Feature Store
- » An Introduction to Meta Learning
- » Explainable AI
- » Design of BigQuery ML
- » Improving Generalization by Self-Training & Self Distillation
- » Neurosymbolic AI
- » Task dependent adaptive metric for improved few-shot learning
- » Variational Continual Learning
- » Lifelong and Continual Learning
- » The Power Of BI (Business Intelligence) in Digital Marketing
- » Urban Computing
- » Urban Computing with Advanced Visualization
- » IEEE ITEC Best Presentation Award
- » Transfer Learning - Part II
- » Transfer Learning - Part I
- » DeepWalk-Turning Graphs Into Features via Network Embeddings
- » Graph Embeddings
- » Deep Learning on Graphs
- » Graph Signal Processing
- » Learning to Learn
- » Exploring And Attacking Neural Networks With Activation Atlases
- » Miracles of Algebraic Graph Theory
- » A History of Spectral Graph Theory and its Applications
- » The JPEG Compression Algorithm
- » Transfer Learning
- » Geometric Deep Learning Papers
- » Controlling Traffic with Reinforcement Learning
- » Ian Goodfellow-Generative Adversarial Networks (GANs)
- » Metric Learning and Manifolds
- » Awesome Knowledge Distillation
- » The Power of Self-Learning Systems
- » Variational Inference-Foundations and Modern Methods
- » 3D Deep Learning
- » Machine Learning on Geometrical Data
- » Hough Transform for Lines
- » Deep Compression
- » Model Compression Papers
- » Deep RL Bootcamp
- » Natural Policy Gradients, TRPO, PPO
- » Deep Learning for Recommender Systems
- » Awesome Knowledge Distillation
- » Knowledge Distillation
- » Distill and transfer learning for robust multitask RL
- » Geometric Deep Learning
- » Visualizing and Understanding Generative Adversarial Networks
- » Trust Region Policy Optimization
- » Generative Adversarial Imitation Learning
- » Google AI's Take on How To Fix Peer Review
- » Towards Generalization and Efficiency in Reinforcement Learning
- » Acceptance Rate of AI Conferences
- » PyTorch Geometric
- » SQL Query Optimization Meets Deep Reinforcement Learning
- » Time Series Forecasting using Statistical and Machine Learning Models
- » BMM Summer Course 2018 Slides
- » A Style-Based Generator Architecture for GAN
- » Multi-Agent Reinforcement Learning
- » What Makes a Good Image Generator AI?
- » Automatic Machine Learning
- » Generalizing Convolutions for Deep Learning
- » Unsupervised Deep Learning
- » Manifold Learning Yields Insight into Complex Biological State Space
- » Project Malmo – a platform for fundamental AI research
- » Keras vs. PyTorch
- » Variational Inference - Foundations and Innovations
- » The GAN Zoo
- » Speed at Scale - Using GPUs to Accelerate Analytics for Extreme Use Cases
- » SpatialHadoop - A MapReduce Framework for Big Spatial Data
- » From Deep Learning of Disentangled Representations to Higher-level Cognition
- » NVIDIA - AI for Generating High-Resolution Images
- » Neural Image Stitching And Morphing
- » Anomaly Detection for Real-World Systems
- » Anomaly Detection
- » What Explains Perception in the Brain?
- » Applied Time Series Econometrics in Python and R
- » Time Series Analysis with Python Intermediate
- » Two Effective Algorithms for Time Series Forecasting
- » AI Learns Painterly Harmonization
- » Deep Learning with Ensembles of Neocortical Microcircuits
- » A Neural Network Model That Can Reason
- » 누구나 할 수 있는 엄청난 몰입력의 5가지 단계
- » This AI Reproduces Human Perception
- » 미루는 버릇을 완전히 없애주는 '2분짜리 간단한 습관'
- » From Generative Models to Generative Agents
- » World Models
- » What Can Machine Learning Do? Workforce Implications
- » Introduction to AI for Video Games
- » 3D Generative-Adversarial Modeling
- » Generative Models
- » The Design of Traffic Flow Prediction System Based on Multimodal Data
- » AI Photo Translation
- » Cluster Analysis
- » Deepmind AlphaZero - Mastering Games Without Human Knowledge
- » NIPS Paper Evaluation Criteria
- » Tutorial on GANs
- » Equilibrium points in n-person games
- » Machine Learning Reports
- » Gaussian Material Synthesis
- » Sequence Generative Adversarial Nets with Policy Gradient
- » The Robot Revolution - The New Age of Manufacturing
- » Evolutionary Generative Adversarial Networks
- » Time Series Generation with Recurrent Conditional GANs
- » Predicting Car Prices using Neural Networks
- » Predicting Car Prices - Linear Regression
- » Deep Reinforcement Learning
- » Brains, Minds and Machines Summer Course
- » OpenAI Meta Learning and Self Play
- » Time Series Analysis
- » Using Support Vector Machines as Flower Finders
- » SARSA vs Q-learning
- » Building a Neural Network Using the Iris Data Set
- » Classification using Decision Trees in R
- » The Long-term of AI & Temporal-Difference Learning
- » Leeds annual traffic growth
- » One pixel attack for fooling deep neural networks
- » Learning From Scratch
- » Cellular Automata
- » Radial basis function (RBFs)
- » Karush-Kuhn-Tucker Condition
- » Boundary Equilibrium Generative Adversarial Networks
- » GAN Tutorials
- » All about the GANs
- » Predicting Congestion with Tensorflow
- » Processing 100 Billion IoT Events
- » Predicting congestion on London's roads with TensorFlow
- » Improving Traffic Prediction Using Weather Data
- » Pruning Makes Faster and Smaller Neural Networks
- » NIPS 2017 Proceedings
- » Distributed TensorFlow
- » This Autonomous Robot Models Your House Interior
- » Reproducibility in Deep Reinforcement Learning
- » Google's Text Reader AI
- » SLAC Dataset From MIT and Facebook
- » DeepMind Control Suite
- » Data Mining Lecture Slides
- » AI Research Trends
- » Data-Driven Mesoscopic Simulation Models
- » Introduction to Geometric Deep Learning
- » Geometric Deep Learning Paper and Code
- » Geometric Deep Learning
- » Building Machines That Learn and Think Like People
- » TensorTraffic
- » Universal Neural Style Transfer
- » Testing Software in the Age of Machine Learning
- » Effective TensorFlow for Non-Experts
- » Gartner Top 10 Strategic Technology Trends 2018
- » Transferring AI To The Real World (OpenAI)
- » Natural Language Processing with Deep Learning
- » Practical Machine Learning Tutorial with Python
- » DeepMind's AI Learns Superhuman Relational Reasoning
- » Multi-Agent Reinforcement Learning
- » Knowledge Based Artificial Intelligence Part 3 ~ 5
- » Knowledge Based Artificial Intelligence Part 2
- » Knowledge Based Artificial Intelligence Part 1
- » AI Learns to Synthesize Pictures of Animals
- » Latent Dirichlet Allocation Concept
- » Mining Massive Data Sets
- » Deep Photo Style Transfer
- » Gunrock - GPU Graph Analytics
- » AI Creates 3D Models From Faces
- » Learning Local Geometric Descriptors from RGB-D Reconstructions
- » Machine Learning APIs by Example
- » Distributed Optimization via Alternating Direction Method of Multipliers
- » Learning and Adaptation
- » Semantic Scene Completion from a Single Depth Image
- » Latent Space Model for Road Networks to Predict Time-Varying Traffic
- » Reinforcement Learning
- » Deep Reinforcement Learning
- » Analysis and Prediction of Spatiotemporal Traffic Congestion
- » Reinforcement Learning Papers
- » Technological Singularity
- » Three Applications of Deep Learning in Big Data Analytics
- » Optimization for Machine Learning
- » Unsupervised Representation Learning
- » Generalization and Equilibrium in Generative Adversarial Networks
- » How to train a GAN
- » Generative Adversarial Networks (GANs)
- » Deep Advances in Generative Modeling
- » A Guide to Edge IoT Analytics
- » Edge Accelerated Web Platform
- » Edge Computing - IoT and Thinking Machine
- » Top AI and Machine Learning Conferences in 2017
- » Fast Data at Internet Scale with Amazon ElastiCache for Redis
- » Fast Data, Fast Monitoring
- » Geometric Detail Transfer
- » Generative Adversarial Networks - Part III
- » Generative Adversarial Networks - Part II
- » Image Editing with Generative Adversarial Networks
- » Generative Adversarial Networks - Part I
- » Can we build AI without losing control over it?
- » The Review Process for NIPS 2016
- » Guidelines for Writing a Good NIPS Paper
- » Graph Streams and Sketches
- » CNNs in Practice
- » Proceedings of The ICML 2016
- » Acceptance Ratio Statistics for Computational Intelligence Conferences
- » Machine Learning Papers in AAAI Conference 2017
- » Three things you need to know about machine learning
- » Artificial Intelligence 3.0 – Third Wave of AI
- » Recent Results in Cloud Robotics
- » Theory, Practice, and Standardization of Eye-tracking Technology
- » Understanding 3D Shapes With AI
- » Occam's Razor
- » Massive Exploration of Neural Machine Translation Architectures
- » 5 Technology Trends in 2017 that Change Your Way of Living
- » The Evolution of Artificial Intelligence
- » How Deep Neural Networks Work
- » Stable Neural Style Transfer
- » GPU accelerated population annealing algorithm
- » Learning Sound Representations from Unlabeled Video
- » Modeling Human Communication Dynamics
- » Improving the Neural GPU Architecture for Algorithm Learning
- » How to Build an Intelligent Machine
- » Introduction to Deep Learning
- » Ten Data Acquisition Strategies for Startups
- » Automatic Creation of Sketch Tutorials
- » Deep Voice; Real-time Neural Text-to-Speech
- » Data, not algorithms, is key to machine learning success
- » The current state of machine intelligence 3.0
- » Optimizing Deep CNN-Based Queries over Video Streams at Scale
- » Gibbs Sampling-Probabilistic Graphical Models
- » AI; The New Electricity
- » Large-Scale Stochastic Learning using GPUs
- » Artificial Intelligence
- » Learning to Fill Holes in Images
- » Journals and Conferences related to Artificial Intelligence
- » AI Builds 3D Models From Images With a Twist
- » Major Conferences and Journals about Machine Learning
- » Most Cited Deep Learning Papers
- » Data Preparation for Machine Learning
- » How to Prepare Data For Machine Learning
- » Deep Natural Language Processing
- » What is Artificial Intelligence?
- » Universe
- » Game AI Development with OpenAI Universe
- » Deep Reinforcement Learning - Pong from Pixels
- » How Intelligent Machines Learn to Make Sense of the World
- » AI Makes 3D Models From Photos
- » Attention Transfer
- » Text Style Transfer
- » IBM Watson-The Power of Artificial Intelligence
- » Adaptive Machine Learning for Real-Time Streaming
- » AI and Deep Learning at Amazon
- » Datasets for Deep Learning
- » DataSets and Machine Learning
- » Open Data for Deep Learning
- » Deep Learning Program Hallucinates Videos
- » Reinforcement Learning
- » Deep Reinforcement Learning
- » Introduction to Deep Learning and Self-Driving Cars
- » Deep Learning Resources
- » Transfer Learning and Fine-tuning Deep Convolutional Neural Networks
- » Machine Learning Algorithms
- » Neural Network Learns The Physics of Fluids and Smoke
- » Recurrent Neural Networks, Image Captioning, LSTM
- » The Unreasonable Effectiveness of Recurrent Neural Networks
- » Understanding LSTM Networks
- » Mathematical Methods for Robotics, Vision, and Graphics
- » Human Pose Estimation with Deep Learning
- » WaveNet by Google DeepMind
- » IBM Watson Health
- » Large Scale Machine Learning
- » Fundamentals of Deep Learning
- » TensorFlow Tutorial
- » TensorFlow Examples
- » Deep Learning Reading List
- » Convolutional Neural Networks for Visual Recognition
- » How to read the genome and build a human being
- » Artistic Style Transfer For Videos
- » Deep Reinforcement Terrain Learning
- » The Intel® Deep Learning Framework
- » Self-Taught Learning and Unsupervised Feature Learning
- » Compiling CUDA C/C++ with LLVM
- » Deep Learning - Intelligence from Big Data
- » How DeepMind's AlphaGo Defeated Lee Sedol
- » The Next Step in GPU-Accelerated Deep Learning
- » Convolutional Neural Networks
- » Awesome Deep Learning
- » Training Deep Neural Networks With Dropout
- » Advanced Operating Systems
- » Machine Learning Courses
- » Deep Learning Terms
- » Deep Learning for Database Performance Optimization
- » No Such Thing As Artificial Intelligence
- » gpucc; an open-source GPGPU compiler
- » 9 Cool Deep Learning Applications
- » Gartner Top 10 Tech Trends for 2016
- » CES 2016 Keynote
- » Rethinking the Role of CPUs in Modern Computers
- » 22nd ACM SIGKDD Conference
- » What is Zeppelin Interpreter
- » Big Data and Machine Learning - Keys to AI Progress
- » Mega-KV, A Case for GPUs to Maximize the Throughput of In-Memory Key-Value Stores
- » Requirements for Cluster Analysis
- » What is Cluster Analysis?
- » Cluster Analysis
- » Setup a JavaCL Maven Project
- » Some Common Parallel Patterns
- » Statistics, Data Mining, Machine Learning and Artificial Intelligence
- » GTC On-Demand
- » Regression Analysis
- » Deep Learning
- » Smart Things vs. Many Experienced Things
- » The Data Science Process
- » Statistical Thinking in the Age of Big Data
- » Populations and Samples
- » Thought Experiment - Meta-Definition
- » A Data Science Profile
- » The Role of the Social Scientist in Data Science
- » What is Data Science? - The Current Landscape
- » What is Data Science?
- » PredictionIO
- » Computational Thinking
parallel computing
- » GPU Acceleration in Kubernetes with Jellyfin
- » A Modern Toolkit for Microservice Communication
- » What Will We Do With Quantum Computing?
- » Road Transport Systems
- » OSPRay
- » Streaming Through Caches
- » GPU Architectures and New Programming Model Features
- » Computer Architecture Essentials
- » What is Quantum Computing?
- » Neuromorphic Chip
- » Graph Partitioning
- » GPU accelerated population annealing algorithm
- » Billion-scale similarity search with GPUs
- » AI; The New Electricity
- » Large-Scale Stochastic Learning using GPUs
- » Spark-GPU; An Accelerated In-Memory Data Processing Engine on Clusters
- » How to read the genome and build a human being
- » The Art of Neural Networks
- » Multithreaded Python with OpenMP
- » Creating an SPMD Vectorizer for OpenCL with LLVM
- » Thread Local Storage
- » Readings in Parallel Computer Architecture
- » Lecture 0 - Course Description and Logistics
- » Parallel Computer Architecture Course
- » Clang MapReduce
- » Multiprocessor Synchronization
- » Unum Computing
- » Extreme Scale Computing
- » Computer Architecture Recommended Readings
- » Introduction to Computer Architecture
- » Lambda Expression in C++
- » Legion Bootcamp
- » RAMCloud Training
- » Kudu - New Apache Hadoop Storage for Fast Analytics on Fast Data
- » GridGain In-Memory Data Fabric
- » Advantages of Functional Programming
- » OpenMOLE
- » Advanced Vector Extension
- » Apache Hadoop vs. IBM Platform Symphony and Infosphere BigInsights
- » How HPC is Hacking Hadoop
- » High-Performance Computing Cluster
- » Introduction to Docker
- » The Bulk Synchronous Parallel Model
- » Data-based parallelism
- » Task-based parallelism
- » Concurrency
- » Serial/Parallel Problems
- » Multinode Computing
- » Grid Architecture and Service Modeling
- » Features of Cloud and Grid Platforms
- » Zero-Copy
- » Remote Direct Memory Access
- » Intel® Xeon Phi™ Coprocessor - the Architecture
- » GPU Cluster
- » GPU Accelerated Computing with C and C++
- » Resource Management Fundamentals
- » Advanced and Distributed Operating Systems
- » Grid Computing
- » Design Objectives of Computer Clusters
- » Clustering for Massive Parallelism
- » Parallel Computing
- » Data-intensive Computing
- » Mapping and Folding and the Map-Reduce Paradigm
- » Functional versus Procedural Programming Models
- » Introduction to Transactional Memory
physical ai
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
protein engineering
- » AI-redesigned starting points and outcomes enhance protein evolution
- » Protein Fold Classification at Scale- Benchmarking and Pretraining
- » Protein Autoregressive Modeling via Multiscale Structure Generation
- » FLIP2: Expanding Protein Fitness Landscape Benchmarks
- » A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
- » Protein Structure Prediction and the Paradigm Shift in Modern Science
- » Protein Thoughts: The Future of Protein Binding in Four Languages
- » Recent Structural Tokenization Research Trends
- » Flow Matching-Based Protein Generation Technology
- » Diffusion-Based Adaptive Tokenization Analysis
- » Protein Structure Tokenization
- » Drug-Discovery-Specific LLMs
- » LLM Covering the Entire Drug Development Cycle
- » AlphaFold 3 & Agentic Drug Discovery
- » AlphaFold 3 & LLM Agents
- » Next-Gen Drug Design: AlphaFold 3 & IsoDDE Fusion
- » Drug Discovery LLM: In-depth Analysis Report
- » AI Innovation for Exploring Unexplored Biological Systems
- » Sequence-Structure Design and Optimization of Unnatural Enzymes
- » The Cell's Sophisticated Engine: Understanding Protein Complexes
- » TxGemma: Open Problems and Vision
- » TxGemma: Major Tasks in Agentic LLM for Drug Discovery
- » TxGemma: An Efficient Agentic LLM for Therapeutics
- » Analysis of Agentic AI for Drug and Material Discovery
- » AI in Inverse Material Design
- » Geometric Deep Learning for Protein Design
- » De Novo Protein Design Using Deep Learning
- » Recent methods for protein structure generation and design
- » Probabilistic Safety Guarantees Using Model Internals
- » How to perform Molecular dynamics simulation in Colab?
- » Diffusion for Molecule Generation
- » From DNA Origami to Protein Design
- » Physics-aware agentic AI to model, design and discover proteins
- » Google AlphaFold3
- » A Natural Fit for Mechanistic Interpretability
- » Protein Design with Guided Discrete Diffusion
- » Large Language Models in Protein; A Comprehensive Survey
- » Analysis and Visualization of Protein-Ligand Interactions
- » Protein design using deep learning
- » De Novo Protein Design
- » Computational Protein Design Then & Now (1988-2024)
technology roadmapping
- » The Singularity: Fiction or Reality?
- » Aging and Technology
- » Technology Valuation and Finance
- » Technology Scouting and Innovation Ecosystems
- » Impact of Technological Innovation on Industrial Ecosystems
- » R&D Project Definition and Portfolio Optimization
- » Military and Intelligence Technologies
- » Knowledge Management and Technology Transfer
- » DNA Sequencing Technology Evolution
- » The Deep Space Network as a Technology Roadmap
- » Technology Infusion Analysis
- » Systems Modeling and Technology Sensitivity Analysis
- » Technology Strategy and Competition
- » From Strategic Drivers to ATRA Portfolio Optimization
- » Technological Diffusion and Disruption
- » The Automobile as a Technology System
- » The Aircraft as a Technology System
- » What Is Technology? A Systems View from Knowledge to Roadmapping
- » From Fire and Steam to Information and the Next Revolution
- » Quantifying Technological Progress
- » Patents and Intellectual Property
- » Biomimetics, Living Machines, and the Cyborg Continuum
world models
- » Agentic Discovery of Executable World Representations
- » ReWorld: An Interactive World Model with Long-Horizon Memory
- » Spatially Grounded Multiscale World Models for AI Co-Scientists
- » Mental World Modeling: Theory of Mind for Agents
- » Towards Human-Level Autonomous Research via Chain-of-Evidence
- » AdaJEPA: An Adaptive Latent World Model
- » Latent Representation for Discovery in Multiscale Physical Fields
- » Deep Research Multi-Agent Framework for Physical Sciences
- » Reversal Q-Learning
- » S-Agent: Hierarchical Tool and Dual Memory-Based Spatial Intelligence
- » From AGI to ASI: Pathways, Bottlenecks, and Theoretical Frameworks
- » MiniMax Sparse Attention (MSA) Analysis
- » The Evolution and Applications of Selective State-Space Models
- » Bebop: Multi-Token Prediction and Rejection Sampling System for LLM
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » Video World Model Utilizing Latent Spatial Memory
- » Analysis of the 5-Stage Industry Hierarchy of the AI Ecosystem
- » Two Methods of AI: 'Verbal Reasoning' and 'Visual Simulation'
- » A Comprehensive Analysis of Visual Generative Distillation Framework
- » Structural Transformation of Biological Intelligence and Digital Intelligence
- » Cosmos 3: Omnimodal World Models for Physical AI
- » NVIDIA Cosmos 3 & The Rise of Omnimodal World Models
- » Beyond Vibe Coding: The Rise of SDD
- » Evolution from a Collaboration Model to a Mechanical Verification Model
- » Architectural Intelligence: Synergistic AI-Aided Design and MAS
- » Specification-Driven Development
- » Beyond Transformers: Exploring the Architecture Shifts
- » Recursive Flow Matching: Generative Model for Physics Simulation
- » Neural World Models
- » Information Bottleneck Driven Tree-based Policy Optimization
- » Bidirectional Evolutionary Exploration for the Self-Evolution of LLMs
- » Hybrid Neural Proxy Model Physicals Acceleration Strategy
- » Next-Generation Robotics Intelligence: VLA vs JEPA
- » Innovation in Gamma-World and Multi-Agent World Modeling
- » AlphaFold-based AI Drug Discovery: Technology Analysis Roadmap
- » Agentic AI New Paradigm
- » TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
- » Qwen-VLA: Universal Robot Agent Analysis Based on VLA Integration
- » Convergence of LLMs and Graph Representation Learning
- » How LLMs Map Human Perceptual Geometry
- » Superintelligence AI Governance and Einstein Test Analysis
- » Evaluation of the Scientific Discovery Capabilities of AI Agents
- » LocateAnything: One Box at a Time
- » HumanEgo: Zero-Shot Robot Learning from Minutes of Egocentric Videos
- » Biology-Inspired AI & Organic Learning
- » AI-based Autonomous Scientific Discovery
- » Co-Scientist-Based Intelligent Drug Development Acceleration
- » Analysis of Multi-Agent AI Frameworks for Accelerated Scientific Discovery
- » Agentic AI and the Rise of World Models
- » World Models as a Next-Generation AI Paradigm
- » Evolution of World Models for Robot Policy Learning
- » Next-Generation AI Architecture: JEPA vs. GLP
- » Evolution of Intelligence: Beyond Generative AI
- » Gaussian World Models
- » The Magic of 3D Spatial Intelligence
- » The Evolution of Intelligent Architectures
- » New Horizons in Video-Language Joint Embedding (VL-JEPA)
- » Overview of Compositional World Models
- » From Data Reliance to Physical Common Sense
- » A Key Driver for Next-Generation World Models
- » Foundation World Models - The Future Of Spatial Intelligence.
- » New horizons in spatial intelligence - World Models
- » Innovative Technologies Leading The World Model Competition
- » World Models - Transformers vs. Spatial Latent Space
- » The New Frontier of Spatial Intelligence
- » World Models for Spatial Intelligence
- » Spatial Intelligence and World Model Frameworks
- » World Models - Intelligence that understands and changes reality
- » Project Genie - New Horizons in Generative AI