Research Papers
Search Results
Research Papers
240 papers in library
2026-09-01
2026-08-3119
- Sheaf Cohomology of Linear Predictive Coding Networks
- Philosophy of Geometry from Riemann to Poincare
- Where Are the Missing Masses? The Sociology of a Few Mundane Artifacts
- On Actor-Network Theory: A Few Clarifications
- Reviving the Philosophy of Geometry
- The Shape of Experience
- The Chemical Basis of Morphogenesis
- Artificial Intelligence and the Structure of Mathematics
- Lenia - Biology of Artificial Life
- Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit
- The Glider Equation for Asymptotic Lenia
- Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery
- Gradients are Not All You Need
- Mathematicians in the age of AI
- Proof Theory and Dependent Type Theory: Distinct Foundations for Designing Proof Assistants
- Some Proposals for Reviving the Philosophy of Mathematics
- Why Pure Reasoning is Not Enough: Nature as the Source of Mathematical Innovation
- Proof Theory and Interpolation for Sacchetti's Logics
- LANA_report_202607/LANA_report_202607.pdf at pdf · katobungen/LANA_report_202607
2026-08-11
2026-07-315
- Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
- A correspondence problem for mathematical proof
- Coxeter and Dynkin Diagrams
- A Study of BFLOAT16 for Deep Learning Training
- A Study of BFLOAT16 for Deep Learning Training
2026-06-112
2026-05-283
2026-05-02
2026-04-055
2026-02-2713
- Graph Representations for Higher-Order Logic and Theorem Proving
- EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
- LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
- DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
- Aristotle: IMO-level Automated Theorem Proving
- Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
- Leanabell-Prover: Posttraining Scaling in Formal Reasoning
- Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
- Sheaf Theory through Examples (Abridged Version)
- Group Theory in a Nutshell for Physicists
- Lean Finder: Semantic Search for Mathlib That Understands User Intents
2026-02-263
2026-02-132
- An Introduction to Sheaves on Grothendieck Topologies
- A CATEGORICAL INTRODUCTION TO SHEAVES
2026-02-03
2026-01-23
2026-01-17
- An Introduction to Topos Theory
2026-01-11
2026-01-10
2026-01-0924
- Classical Sorting Algorithms as a Model of Morphogenesis: self-sorting arrays reveal unexpected competencies in a minimal model of basal intelligence
- Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata
- Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
- A Background Independent Algebra in Quantum Gravity
- LLMSTEP: LLM proofstep suggestions in Lean
- miniCTX: Neural Theorem Proving with (Long-)Contexts
- AI-Assisted Generation of Difficult Math Questions
- Categorical Proof-Theoretic Semantics
- Graph Representations for Higher-Order Logic and Theorem Proving
- EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty
- Categorical Proof-Theoretic Semantics
- EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Hilbert $*$-categories: Where limits in analysis and category theory meet
- Basic Category Theory
- Coend calculus
- LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
- DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
- Aristotle: IMO-level Automated Theorem Proving
- Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
- Leanabell-Prover: Posttraining Scaling in Formal Reasoning
- Premise Selection for a Lean Hammer
- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
- Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
2026-01-04
2026-01-022
2025-12-22
2025-12-15
2025-12-134
2025-12-107
- Transformers know more than they can tell -- Learning the Collatz sequence
- Forms of life, forms of mind | Dr. Michael Levin | Algorithms Redux: finding unexpected properties in truly minimal systems
- Learning in Transcriptional Network Models: Computational Discovery of Pathway-Level Memory and Effective Interventions
- Top-down models in biology: explanation and control of complex living systems above the molecular level
- Darwin’s agential materials: evolutionary implications of multiscale competency in developmental biology
- Technological Approach to Mind Everywhere: An Experimentally-Grounded Framework for Understanding Diverse Bodies and Minds
- The Universal Weight Subspace Hypothesis
2025-12-082
2025-12-022
2025-11-28
2025-11-22
2025-11-17
2025-11-062
2025-11-04
2025-10-30
2025-10-082
2025-09-25
2025-09-22
2025-09-11
2025-09-015
2025-08-112
2025-08-05
2025-08-01
2025-07-28
2025-07-232
2025-07-162
2025-07-15
2025-07-12
2025-07-09
2025-07-08
2025-07-06
2025-07-01
2025-06-2810
- Magistral
- Reinforcement Pre-Training
- Trends in AI Supercomputers
- eGPU: Extending eBPF Programmability and Observability to GPUs
- Attention-Level Speculation
- Qwen3 Technical Report
- LazyLog: A New Shared Log Abstraction for Low-Latency Applications
- How Much Knowledge Can You Pack Into the Parameters of a Language Model?
- The empirical status of predictive coding and active inference
- Predictive eye movements are adjusted in a Bayes-optimal fashion in response to unexpectedly changing environmental probabilities
2025-06-27
2025-06-262
2025-06-25
2025-06-17
2025-06-132
2025-06-124
2025-06-102
2025-06-09
2025-06-0523
- Minimum Description Length and Generalization Guarantees for Representation Learning
- Compute-Optimal LLMs Provably Generalize Better With Scale
- Large Language Model Compression with Global Rank and Sparsity Optimization
- A Survey to Recent Progress Towards Understanding In-Context Learning
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- The Complexity Dynamics of Grokking
- Denoising Diffusion Probabilistic Models
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Mechanistic Design and Scaling of Hybrid Architectures
- Mathematical discoveries from program search with large language models
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Trade-offs in Data Memorization via Strong Data Processing Inequalities
- What Formal Languages Can Transformers Express? A Survey
- The Illusion of State in State-Space Models
- Let’s Think Dot by Dot: Hidden Computation in Transformer Language Models
- Emerging Properties in Unified Multimodal Pretraining
- How much do language models memorize?
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization
- ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
2025-06-034
- Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs
- AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
2025-06-02
2025-06-01
2025-05-31
2025-05-283
2025-05-252
2025-05-244
2025-05-167
- Round and Round We Go! What makes Rotary Positional Encodings useful?
- HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Transformers Represent Belief State Geometry in their Residual Stream
- Consequences of the Moosbauer-Poole Algorithms
- Emergence of Language in the Developing Brain
- Illuminating search spaces by mapping elites
2025-05-152
2025-05-12
2025-05-11
2025-05-10
2025-05-066
- A Path Towards Autonomous Machine Intelligence Version 0.9.2, 2022-06-27
- Learning high-level visual representations from a child's perspective without strong inductive biases
- Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers
- Scaling Laws for Precision
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
- Learning to Reason for Long-Form Story Generation
2025-05-04
2025-05-038
- Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
- Similarity of Neural Network Representations Revisited
- Layers at Similar Depths Generate Similar Activations Across LLM Architectures
- What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
- TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- History, Development, and Principles of Large Language Models-An Introductory Survey
- Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
2025-04-27
2025-04-265
- Progress measures for grokking via mechanistic interpretability
- Towards Automated Circuit Discovery for Mechanistic Interpretability
- Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
- Circuit Tracing: Revealing Computational Graphs in Language Models
- On the Biology of a Large Language Model
2025-04-246
- Generalization through variance: how noise shapes inductive biases in diffusion models
- GENERALIZATION THROUGH VARIANCE: HOW NOISE SHAPES INDUCTIVE BIASES IN DIFFUSION MODELS
- Training Large Language Models to Reason in a Continuous Latent Space
- Contextualization Machines
- Training Large Language Models to Reason in a Continuous Latent Space
- Do Llamas Work in English? On the Latent Language of Multilingual Transformers
2025-02-172
Timeline
Loading timeline…