LudwigAbap

cs.AI

Subcategories

Papers

paper Juergen Schmidhuber · 2009 Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes cs.AI cs.NE

paper Bruno Gavranović · 2024 Position: Categorical Deep Learning is an Algebraic Theory of All Architectures cs.AI cs.LG math.CT math.RA stat.ML

paper Aditya Paliwal · 2019 Graph Representations for Higher-Order Logic and Theorem Proving cs.AI cs.LG cs.LO stat.ML
paper Yuchen Tian · 2025 EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty cs.AI
paper Michael M. Bronstein · 2021 Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges cs.AI cs.CG cs.CV cs.LG stat.ML
paper Matěj Kripner · 2025 LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4 cs.AI cs.LG
paper Huajian Xin · 2024 DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search cs.AI cs.CL cs.LG cs.LO
paper Tudor Achim · 2025 Aristotle: IMO-level Automated Theorem Proving cs.AI cs.CL
paper Peiyang Song · 2025 Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean cs.AI cs.LG cs.LO stat.ML
paper Jingyuan Zhang · 2025 Leanabell-Prover: Posttraining Scaling in Formal Reasoning cs.AI
paper Xingwei Qu · 2026 Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space cs.AI cs.LG

paper Taining Zhang · 2023 Classical Sorting Algorithms as a Model of Morphogenesis: self-sorting arrays reveal unexpected competencies in a minimal model of basal intelligence cs.AI cs.DS cs.MA cs.NE
paper Erwan Plantec · Artificial Life 2025 Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata cs.AI nlin.CG
paper Xingwei Qu · 2026 Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space cs.AI cs.LG
paper Sean Welleck · 2023 LLMSTEP: LLM proofstep suggestions in Lean cs.AI cs.LG
paper Jiewen Hu · 2025 miniCTX: Neural Theorem Proving with (Long-)Contexts cs.AI cs.CL cs.LG
paper Vedant Shah · 2025 AI-Assisted Generation of Difficult Math Questions cs.AI cs.LG
paper Aditya Paliwal · 2019 Graph Representations for Higher-Order Logic and Theorem Proving cs.AI cs.LG cs.LO stat.ML
paper Yuchen Tian · 2025 EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty cs.AI
paper Yuchen Tian · 2025 EvolProver: Advancing Automated Theorem Proving by Evolving Formalized Problems via Symmetry and Difficulty cs.AI
paper Michael M. Bronstein · 2021 Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges cs.AI cs.CG cs.CV cs.LG stat.ML
paper Matěj Kripner · 2025 LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4 cs.AI cs.LG
paper Huajian Xin · 2024 DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search cs.AI cs.CL cs.LG cs.LO
paper Tudor Achim · 2025 Aristotle: IMO-level Automated Theorem Proving cs.AI cs.CL
paper Peiyang Song · 2025 Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean cs.AI cs.LG cs.LO stat.ML
paper Jingyuan Zhang · 2025 Leanabell-Prover: Posttraining Scaling in Formal Reasoning cs.AI
paper Thomas Zhu · 2025 Premise Selection for a Lean Hammer cs.AI cs.LG cs.LO
paper Kaiyu Yang · 2023 LeanDojo: Theorem Proving with Retrieval-Augmented Language Models cs.AI cs.LG cs.LO stat.ML
paper Bruno Gavranović · 2024 Position: Categorical Deep Learning is an Algebraic Theory of All Architectures cs.AI cs.LG math.CT math.RA stat.ML

paper Alex L. Zhang · 2025 Recursive Language Models cs.AI cs.CL

paper Fiona Y. Wang · 2025 Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation cond-mat.mes-hall cond-mat.soft cs.AI cs.CL cs.LG

paper Max Y. Ma · 2025 Deep Manifold Part 2: Neural Network Mathematics cs.AI cs.LG
paper Juergen Schmidhuber · 2015 On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models cs.AI cs.LG cs.NE

paper Prakhar Kaushik · 2025 The Universal Weight Subspace Hypothesis cs.AI cs.CV cs.LG

paper Chris Cummins · 2024 Meta Large Language Model Compiler: Foundation Models of Compiler Optimization cs.AI cs.PL

paper Taining Zhang · 2023 Classical Sorting Algorithms as a Model of Morphogenesis: self-sorting arrays reveal unexpected competencies in a minimal model of basal intelligence cs.AI cs.DS cs.MA cs.NE

paper Quang Pham · 2022 Continual Learning: Fast and Slow cs.AI cs.CV cs.LG
paper Jack Bell · 2025 The Future of Continual Learning in the Era of Foundation Models: Three Key Directions cs.AI cs.LG

paper Kaiyue Wen · 2025 Fantastic Pretraining Optimizers and Where to Find Them cs.AI cs.LG stat.ML

paper Cunxi Yu · 2025 Autonomous Code Evolution Meets NP-Completeness cs.AI cs.LG cs.LO

paper Jordi Grau-Moya · 2024 Learning Universal Predictors cs.AI cs.LG
paper Jun Wan · 2025 Large Language Models as Computable Approximations to Solomonoff Induction cs.AI cs.CL cs.LG

paper Dan A. Calian · 2025 DataRater: Meta-Learned Dataset Curation cs.AI cs.LG stat.ML

paper Mihir Prabhudesai · 2025 Diffusion Beats Autoregressive in Data-Constrained Settings cs.AI cs.CV cs.LG cs.RO
paper Alex Cloud · 2025 Subliminal Learning: Language models transmit behavioral traits via hidden signals in data cs.AI cs.LG

paper David C. Krakauer · 2025 Large Language Models and Emergence: A Complex Systems Perspective cs.AI cs.CL cs.LG cs.NE

paper Aurko Roy · 2025 Fast and Simplex: 2-Simplicial Attention in Triton cs.AI cs.LG

paper Shiyang Zhang · 2025 Intelligence at the Edge of Chaos cs.AI cs.NE

paper Konstantin F. Pilz · 2025 Trends in AI Supercomputers cs.AI cs.CY

paper Luke Darlow · 2025 Continuous Thought Machines cs.AI cs.LG

paper Subham Sekhar Sahoo · 2025 The Diffusion Duality cs.AI cs.CL cs.LG

paper C. Opus · 2025 Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity cs.AI cs.LG

paper Hugh Zhang · 2023 Chain-of-Thought Reasoning is a Policy Improvement Operator cs.AI cs.CL cs.LG
paper Jonathan Richens · 2025 General agents need world models cs.AI cs.LG cs.RO stat.ML
paper Shibo Hao · 2023 Reasoning with Language Model is Planning with World Model cs.AI cs.CL cs.LG

paper Marc Finzi · 2025 Compute-Optimal LLMs Provably Generalize Better With Scale cs.AI cs.LG
paper Changhai Zhou · 2025 Large Language Model Compression with Global Rank and Sparsity Optimization cs.AI cs.LG
paper Jenny Zhang · 2025 Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents cs.AI
paper Michael M. Bronstein · 2021 Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges cs.AI cs.CG cs.CV cs.LG stat.ML
paper Mingjie Liu · 2025 ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models cs.AI cs.CL

paper Alexander K. Lew · 2023 Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs cs.AI cs.CL cs.PL stat.CO
paper Yang Chen · 2025 AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning cs.AI cs.CL cs.LG
paper Yang Yue · 2025 Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? cs.AI cs.CL cs.CV
paper Shenzhi Wang · 2025 Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning cs.AI cs.CL cs.LG

paper Zafir Stojanovski · 2025 REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards cs.AI cs.CL cs.LG

paper Jessy Lin · 2024 Learning to Model the World with Language cs.AI cs.CL cs.LG

paper Aske Plaat · 2022 Deep Reinforcement Learning, a textbook cs.AI cs.LG

paper Andrew Zhao · 2025 Absolute Zero: Reinforced Self-play Reasoning with Zero Data cs.AI cs.CL cs.LG

paper Yi Xu · 2025 Visual Planning: Let's Think Only with Images cs.AI cs.CL cs.CV cs.LG
paper Minyoung Huh · 2024 The Platonic Representation Hypothesis cs.AI cs.CV cs.LG cs.NE

paper Jean-Baptiste Mouret · 2015 Illuminating search spaces by mapping elites cs.AI cs.NE cs.RO q-bio.PE

paper Adityanarayanan Radhak... · 2023 Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features cs.AI cs.LG stat.ML

paper Guanzhi Wang · 2023 Voyager: An Open-Ended Embodied Agent with Large Language Models cs.AI cs.LG

paper Liqun Ma · 2024 FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation cs.AI cs.CL cs.LG

paper Christopher Wolfram · 2025 Layers at Similar Depths Generate Similar Activations Across LLM Architectures cs.AI cs.CL
paper Qiyuan Zhang · 2025 What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models cs.AI cs.CL
paper Mahmoud Assran · 2023 Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture cs.AI cs.CV cs.LG eess.IV
paper Zicheng Lin · 2025 Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability cs.AI cs.CL cs.LG

paper Andrew M. Saxe · Proceedings of the... 2019 A mathematical theory of semantic development in deep neural networks cs.AI cs.LG q-bio.NC stat.ML

paper Neel Nanda · 2023 Progress measures for grokking via mechanistic interpretability cs.AI cs.LG
paper Juergen Schmidhuber · 2009 Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes cs.AI cs.NE

paper Guanghao Ye · 2025 On the Emergence of Thinking in LLMs I: Searching for the Right Intuition cs.AI cs.CL cs.LG