AGI
General
•
2408 - A Theory of Understanding for Artificial Intelligence: Composability, Catalysts, and Learning
•
2406 - Open-Endedness is Essential for Artificial Superhuman Intelligence
•
2311 - Levels of AGI: Operationalizing Progress on the Path to AGI
•
2208 - The Alberta Plan for AI Research
AI Mathematician / AI Scientist / Autoformalization
General
•
2504 - Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
•
2504 - Brains vs. Bytes - Evaluating LLM Proficiency in Olympiad Mathematics
•
2502 - Auto-Bench - An Automated Benchmark for Scientific Discovery in LLMs
•
2411 - Large language models surpass human experts in predicting neuroscience results
•
2411 - Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
•
2410 - Herald - A Natural Language Annotated Lean 4 Dataset
•
2407 - LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover
•
2306 - From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
•
2406 - AI-Assisted Generation of Difficult Math Questions
•
2405 - Metacognitive Capabilities of LLMs- An Exploration in Mathematical Problem Solving
•
2405 - DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
•
2404 - A Survey on Deep Learning for Theorem Proving
•
2403 - Don’t Trust: Verify – Grounding LLM Quantitative Reasoning with Autoformalization
•
2403 - Machine Learning and Information Theory Concepts Towards an AI Mathematician [Y. Bengio]
•
2402 - REFACTOR: Learning to Extract Theorems from Proofs
•
•
2312 - Speculative Exploration on the Concept of Artificial Agents Conducting Autonomous Research 
•
2310 - A New Approach Towards Autoformalization
•
2212 - Solving Quantitative Reasoning Problems with Language Models
•
2302 - Peano - Learning Formal Mathematical Reasoning
•
2301 - Towards Autoformalization of Mathematics and Code Correctness: Experiments with Elementary Proofs
•
2210 - Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
•
2205 - Autoformalization with Large Language Models
•
20xx - A Promising Path Towards Autoformalization and General Artificial Intelligence
•
2009 - Generative Language Modeling for Automated Theorem
•
2006 - Mathematical Reasoning via Self-supervised Skip-tree Training
AI4Science
Protein Design
•
2402 - Generative AI for Controllable Protein Sequence Design: A Survey
ARC & VAR
General
•
2411 - LogiCity- Advancing Neuro-Symbolic AI with Abstract Urban Simulation
•
2405 - DAT - Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
•
2403 - Human-Level Few-Shot Concept Induction Through Minimax Entropy Learning
•
2304 - Abstractors and Relational Cross-Attention: An Inductive Bias for Explicit Relational Reasoning in Transformers
ARC
•
2412 - ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)
•
2412 - ARC Prize 2024: Technical Report
•
2411 - Mini-ARC: Solving Abstraction and Reasoning Puzzles with Small Transformer Models
•
2411 - Searching Latent Program Spaces
•
2411 - The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
•
2411 - Combining Induction and Transduction for Abstract Reasoning
•
2410 - Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects
•
2409 - H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
•
2404 - Re-ARC - Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
•
2403 - Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
•
2402 - Neural Networks for Abstraction and Reasoning: Towards Broad Generalization in Machines
•
22xx - A Program-Synthesis Challenge for ARC-Like Tasks
Architectures (Backbone)
General
•
2501 - What’s Next for Mamba? Towards More Expressive Recurrent Update Rules
•
2410 - FACTS- A Factored State-Space Framework For World Modelling
•
2406 - Vision-LSTM: xLSTM as Generic Vision Backbone
•
2405 - Aaren - Attention as an RNN
•
2310 - Sparse Universal Transformer
•
2212 - DiT - Scalable Diffusion Models with Transformers (Backbone Architecture of Sora)
•
2207 - Neural Networks And The Chomsky Hierarchy
•
2202 - GroupViT: Semantic Segmentation Emerges from Text Supervision
•
2202 - MaskGIT: Masked Generative Image Transformer
•
20xx - Theoretical Limitations of Self-Attention in Neural Sequence Models
Artificial Hippocampus & Spatial Intelligence
General
•
2503 - A hippocampal population code for rapid generalization
•
2501 - Computational Models of Hippocampal Cognitive Function
•
2501 - Key-Value Memory in the Brain
•
2412 - Learning Hierarchical Abstractions of Complex Dynamics using Active Predictive Coding Spatial
•
2412 - Models of Human Hippocampal Specialization- a Look at the Electrophysiological Evidence
•
2411 - A Tale of Two Algorithms - Structured Slots Explain Prefrontal Sequence Memory and Are Unified with Hippocampal Cognitive Maps
•
2408 - Space as A Scaffold for Rotational Generalisation of Abstract Concepts
•
2408 - Human hippocampal and entorhinal neurons encode the temporal structure of experience @11/30/2024
•
2408 - How the Human Brain Creates Cognitive Maps of Related Concepts
•
2408 - Why Concepts Are (probably) Vectors
•
2408 - Cognitive maps from predictive vision
•
2408 - Abstract representations emerge in human hippocampal neurons during inference
•
2407 - Space is a latent sequence: A theory of the hippocampus
•
2407 - Automated construction of cognitive maps with visual predictive coding
•
2407 - The Computational Foundations of Dynamic Coding in Working Memory
•
2406 - A recurrent network model of planning explains hippocampal replay and human behavior
•
2405 - Remapping revisited: how the hippocampus represents different spaces
•
2401 - Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments
•
2311 - The generative grammar of the brain: a critique of internally generated representations
•
2308 - Cognitive graphs: Representational substrates for planning
•
2302 - Replay and Compositional Computation
•
2209 - How to build a cognitive map
2112 - Relating Transformers to Models and Neural Representations of The Hippocampal Formation
•
2106 - Geometry of abstract learned knowledge in the hippocampus
•
2009 - Emergence of abstract rules in the primate brain
•
1805 - Vector-Based Navigation Using Grid-Like Representations in Artificial Agents
Spatial AI
Causality
Position & Survey Papers
•
2409 - Theory Is All You Need: AI, Human Cognition, and Causal Reasoning
•
2405 - From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
•
2403 - Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
•
2402 - Essential Role of Causality in Foundation World Models for Embodied AI
•
2307 - Causal Reinforcement Learning: A Survey
•
2302 - A Survey on Causal Reinforcement Learning
•
2206 - Causal Machine Learning: A Survey
•
2105 - Toward Causal Representation Learning
RL & World Model
•
2501 - Language Agents Meet Causality -- Bridging LLMs and Causal World Models
•
2408 - Rethinking State Disentanglement in Causal Reinforcement Learning
•
2406 - Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
•
2404 - Robust Agents Learn Causal World Models
•
2404 - Compete and Compose: Learning Independent Mechanisms for Modular World Models
•
2404 - Empowerment as Causal Learning, Causal Learning as Empowerment A bridge between Bayesian causal hypothesis testing and reinforcement learning
•
2403 - Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization
•
2306 - Granger Causal Interaction Skill Chains
•
2206 - Causal Dynamics Learning for Task-Independent State Abstraction
•
2200 - CausalDyna: Improving Generalization of Dyna-Style Reinforcement Learning via Counterfactual-Based Data Augmentation
•
2102 - Agent Incentives - A Causal Perspective
•
2100 - Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Causal-LLM
•
2502 - Auto-Bench- An Automated Benchmark for Scientific Discovery in LLMs
•
2412 - Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation
•
2412 - Do LLMs Act as Repositories of Causal Knowledge?
•
2402 - Efficient Causal Graph Discovery Using Large Language Models
Representation
•
2409 - Unifying Causal Representation Learning with the Invariance Principle
•
2407 - Disentangled Representations for Causal Cognition
•
2406 - The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning
•
2405 - From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
•
24xx - Multi-View Causal Representation Learning with Partial Observability
•
2403 - Towards the Reusability and Compositionality of Causal Representations
•
2305 - Interventional Causal Representation Learning
•
2310 - Towards Causal Foundation Model: on Duality between Causal Inference and Attention
•
23xx - Nonparametric Identifiability of Causal Representations from Unknown Interventions
•
2209 - Interventional Causal Representation Learning
•
2203 - Weakly Supervised Causal Representation Learning
•
2202 - CITRIS: Causal Identifiability from Temporal Intervened Sequences
•
2100 - CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models
•
2000 - iVAE: Variational Autoencoders and Nonlinear ICA: A Unifying Framework
•
13xx - Programs as Causal Models - Speculations on MentalPrograms and Mental Representation
Discovery
•
2405 - Demystifying Amortized Causal Discovery with Transformers
•
2402 - Efficient Causal Graph Discovery Using Large Language Models
•
2206 - Causal Dynamics Learning for Task-Independent State Abstraction
•
2204 - Learning to Induce Causal Structure
•
2202 - DECI - Deep End-to-end Causal Inference
•
2011 - Causal Autoregressive Flows
•
20xx - Causal Discovery with Reinforcement Learning
•
20xx - Differentiable Causal Discovery from Interventional Data
Benchmarks
•
2405 - Smoke and Mirrors in Causal Downstream Tasks
Causality in NeuroCog
•
2409 - Theory Is All You Need: AI, Human Cognition, and Causal Reasoning
•
2406 - Counterfactual Simulation in Causal Cognition (by Tobias Gerstenberg)
•
2405 - The Development of Human Causal Learning and Reasoning
•
2001 - What is Causal Cognition
•
1707 - Changes in cognitive flexibility and hypothesis searchacross human life history from childhood toadolescence to adulthood
Compositionality
Position Papers
•
2402 - Compositional Generative Modeling - A Single Model is Not All You Need
•
2302 - Modular Deep Learning
General
•
2411 - Interaction Asymmetry - A General Principle For Learning Composable Abstractions
•
2407 - Deciphering the Role of Representation Disentanglement - Investigating Compositional Generalization in CLIP Models
•
2406 - Discrete Dictionary-based Decomposition Layer for Structured Representation Learning TPR Vision
•
2310 - Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
•
1908 - The Compositionality of Neural Networks: Integrating Symbolism and Connectionism [Hupkes]
Algorithmic
•
2303 - The New XOR Problem
Composable World Models
•
2404 - Compete and Compose: Learning Independent Mechanisms for Modular World Models
•
20xx - Compositional Visual Generation with Energy Based Models [Igor Mordarch]
Neural Programmer
•
2306 - Learning Transformer Programs
Backbone Architectures (Compositional Transformer)
•
2405 - Transformers Can Do Arithmetic with the Right Embeddings
•
2405 - Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
•
2405 - Improving Transformers with Dynamically Composable Multi-Head Attention
•
2405 - Sparo: Selective Attention for Robust and Compositional Transformer Encodings for Vision
•
2404 - When Can Transformers Reason with Abstract Symbols?
•
2311 - Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
•
2311 - What Algorithms can Transformers Learn? A Study in Length Generalization
•
22xx - Making Transformers Solve Compositional Tasks
•
2110 - Compositional Attention: Disentangling Search and Retrieval
Emergent Communication
•
2408 - Emergent Language in Open-Ended Environments
•
2406 - Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
NeuroCog
•
2407 - Modularity in Biologically Inspired Representations Depends on Task Variable Range Independence
•
2406 - Binding in Hippocampal-Entorhinal Circuits Enables Compositionality in Cognitive Maps
•
2405 - The relational bottleneck as an inductive bias for efficient abstraction
•
2304 - Constructing Future Behaviour in The Hippocampal Formation Through Composition and Replay
•
2305 - Neural Knowledge Assembly in Humans and Neural Networks [Christopher Summerfield]
•
2304 - Hippocampal Spatio-Predictive Cognitive Maps Adaptively Guide Reward Generalization
•
2209 - Symbols and Mental Programs: A Hypothesis About Human Singularity [Stanislas Dehaene]•
2211 - Fast rule switching and slow rule updating in a perceptual categorization task [N. Daw]
•
2010 - Meta-Learning of Compositional Task Distributions in Humans and Machines [Thomas L. Griffiths]
•
20xx - Concepts and Compositionality - In Search of the Brain’s Language of Thought
Consciousness
NeuroCog
•
2407 - Conscious Artificial Intelligence and Biological Naturalism
•
2407 - What Does Decoding from The PFC Reveal About Consciousness? [Ned Block]
Diffusion Models
Tutorial
•
2406 - Step-by-Step Diffusion - An Elementary Tutorial
•
2405 - Building Diffusion Model's theory from ground up
•
2403 - Tutorial on Diffusion Models for Imaging and Vision
•
2401 - Demystifying Variational Diffusion Models
•
2208 - Understanding Diffusion Models - A Unified Perspective
Foundation
•
2411 - Towards a Mechanistic Explanation of Diffusion Model Generalization
•
2410 - One Step Diffusion via Shortcut Models Efficiency
•
2406 - Variational Flow Matching for Graph Generation Flow Matching
•
2312 - Boosting Latent Diffusion with Flow Matching Flow Matching
•
2307 - Flow Matching in Latent Space Flow Matching
•
2211 - Efficient Video Prediction via Sparsely Conditioned Flow Matching Flow Matching
•
2210 - Flow Matching for Generative Modeling Flow Matching
•
2209 - Diffusion Posterior Sampling for General Noisy Inverse Problems Inverse Problem
•
2207 - Classifier-Free Diffusion Guidance Guidance
•
2202 - Progressive Distillation for Fast Sampling of Diffusion Models Efficiency
•
2105 - Diffusion Models Beat GANs on Image Synthesis [→ Classifier-Guidance] Guidance
•
2010 - DDIM - Denoising Diffusion Implicit Models
•
2006 - DDPM - Denoising Diffusion Probabilistic Models
Discrete Diffusion
•
2503 - Block Diffusion - Interpolating Between Autoregressive and Diffusion Language Models
•
2503 - Generalized Interpolating Discrete Diffusion
•
2502 - Spatial Reasoning with Denoising Models
•
2412 - Simple Guidance Mechanisms For Discrete Diffusion Models Guidance Discrete
•
2410 - G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving Discrete
•
2408 - Discrete Flow Matching Discrete
•
2406 - Simple and Effective Masked Diffusion Language Models Discrete
•
2406 - Simplified and Generalized Masked Diffusion for Discrete Data Discrete
•
2310 - SEDD - Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution Discrete
•
2107 - D3PM - Structured Denoising Diffusion Models in Discrete State-Spaces Discrete
•
2102 - Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions Discrete
Diffusion Posterior Sampling (Diffusion + SMC)
•
2412 - On Diffusion Posterior Sampling via Sequential Monte Carlo for Zero-Shot Scaffolding of Protein Motifs
•
2405 - Diffusion Posterior Sampling for Linear Inverse Problem Solving — a Filtering Perspective
•
2312 - Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
Discrete Representation (VQ-VAE)
General
•
2408 - Discrete Flow Matching
•
2407 - Balance of Number of Embedding and their Dimensions in Vector Quantization
•
23xx - Resizing Codebook of Vector Quantization without Retraining
•
23xx - Straightening out The Straight through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
•
2310 - EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders
•
2309 - Finite Scalar Quantization: VQ-VAE Made Simple
•
2303 - Regularized Vector Quantization for Tokenized Image Synthesis
•
22xx - SQ-VQE: Variational Bayes on Discrete Representation with Self-Annealed Stochastic Quantization
•
22xx - Discrete Representations Strengthen Vision Transformer Robustness
•
2102 - dVAE - Zero-Shot Text-to-Image Generation
•
20xx - Hierarchical Quantized Autoencoders
•
1711 - VQ-VAE - Neural Discrete Representation Learning
Exploration
General
•
2206 - BYOL-Explore: Exploration by Bootstrapped Prediction
GFlowNets
General
•
2412 - Amortizing Intractable Inference in Diffusion Models for Bayesian Inverse Problems
•
2410 - Adaptive Teachers For Amortized Samplers
•
2405 - Amortizing Intractable Inference in Diffusion Models for Vision, Language, and Control
•
24XX - Maximum Entropy GFlowNets with Soft Q-Learning
•
24XX - Generative Flow Networks as Entropy-Regularized RL
•
2310 - Local Search GFlowNets
•
2302 - DynGFN - Bayesian Dynamic Causal Discovery using Generative Flow Networks
•
2209 - SubTB - Learning GFlowNets from Partial Episodes for Improved Convergence and Stability
Interactive Embodied Agents
General
•
2310 - SmartPlay - A Benchmark for LLMs as Intelligent Agents
Robotics
•
2406 - DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
•
2406 - Language Guided Skill Discovery
•
2405 - Vision-based Manipulation from Single Human Video with Open-World Object Graphs
•
2405 - From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
•
2312 - SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
•
2307 - Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
•
2210 - Language-Table: Interactive Language - Talking to Robots in Real Time
Minecraft
•
2407 - Odyssey: Empowering Agents with Open-World Skills
•
2403 - MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control
•
2312 - MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception
Crafter
•
2404 - AgentKit: Structured LLM Reasoning with Dynamic Graphs
LLMs
Position Papers & Survey
•
2406 - From Decoding to Meta-Generation- Inference-time Algorithms for Large Language Models
•
2402 - Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
LLM Agent
•
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
LLM Reasoning
•
2504 - Brains vs. Bytes- Evaluating LLM Proficiency in Olympiad Mathematics
•
2501 - DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
•
2501 - rStar-Math- Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking Math
•
2412 - Scaling of Search and Learning - A Roadmap to Reproduce o1 from Reinforcement Learning Perspective o1 Reasoning
•
2412 - Mastering Board Games by External and Internal Planning with Language Models
•
2412 - Training Large Language Models to Reason in a Continuous Latent Space
•
24xx - SELF-EXPLORE - Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
•
2411 - Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
•
2409 - RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
•
2409 - Looped Transformers for Length Generalization
•
2408 - Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
•
2407 - NuminaMath - The largest public dataset in AI4Maths with 860k pairs of competition math problems and solutions Benchmark
•
2407 - Recursive Introspection - Teaching Language Model Agents How to Self-Improve
•
2407 - Deciphering the Factors Influencing the Efficacy of Chain-of-Thought- Probability, Memorization, and Noisy Reasoning
•
2406 - Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
•
2405 - Learning to Reason via Program Generation, Emulation, and Search
•
2405 - From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
•
2405 - AlphaMath Almost Zero - Process Supervision Without Process
•
2405 - Understanding Transformer Reasoning Capabilities via Graph Algorithms
•
2405 - From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
•
2404 - Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
•
2403 - Machine Learning and Information Theory Concepts Towards an AI Mathematician
•
2402 - Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
•
2312 - Math-Shepherd - Verify and Reinforce LLMs Step-by-step without Human Annotations
•
23xx - Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design
•
23xx - Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
•
2309 - AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
•
2308 - Reinforced Self-Training (ReST) for Language Modeling
•
2308 - Graph of Thoughts - Solving Elaborate Problems with Large Language Models
•
2305 - Let’s Verify Step by Step
•
2305 - Reasoning with Language Model is Planning with World Model
•
2302 - On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)
•
2212 - Prompting Is Programming- A Query Language for Large Language Models
•
2210 - Language Models Are Greedy Reasoners- A Systematic Formal Analysis Of Chain-Of-Thought
•
2110 - Training Verifiers to Solve Math Word Problems
GPT-o1 Analysis
•
2411 - o1-Coder: an o1 Replication for Coding
•
2411 - Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
•
2410 - When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1
•
O1 Replication Journey – Part 2: Surpassing O1-preview through Simple Distillation Big Progress or Bitter Lesson?
Causal
•
2402 - Efficient Causal Graph Discovery Using Large Language Models
Understanding
•
2406 - Transformers need glasses! Information over-squashing in language tasks
•
2406 - The Geometry of Categorical and Hierarchical Concepts in Large Language Models
In Brain
•
1709 - Language, Mind and Brain
Memory
General
•
2405 - The Memory Systems of The Human Brain and Generative Artificial Intelligence
•
2405 - In Search of Dispersed Memories: Generative Diffusion Models Are Associative Memory Networks
•
2212 - Retrieval-Augmented Diffusion Models
Associative Memory
•
2501 - Titans - Learning to Memorize at Test Time
•
2501 - Episodic and Associative Memory From Spatial Scaffolds In The Hippocampus neurocog
•
2501 - Test-time regression - a unifying framework for designing sequence models with associative memory
•
2412 - Memorization to Generalization: The Emergence of Diffusion Models from Associative Memory
•
2412 - Memory Layers at Scale
•
2405 - Memory Mosaics
2406 - Parallelizing Linear Transformers with the Delta Rule over Sequence Length
NeuroCog
•
2306 - Organizing memories for generalization in complementary learning systems
NeuroAI & NeuroCog General
General
•
2412 - Models of human hippocampal specialization- a look at the electrophysiological evidence
•
2411 - A Tale of Two Algorithms - Structured Slots Explain Prefrontal Sequence Memory and Are Unified with Hippocampal Cognitive Maps
•
2409 - A Neural Mechanism for Compositional Generalization of Structure in Humans
•
2405 - Curiosity and The Dynamics of Optimal Exploration
•
2308 - Cognitive graphs: Representational substrates for planning
•
23xx - Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
•
2209 - Symbols and Mental Programs: A Hypothesis About Human Singularity
Traveling Waves
•
2309 - wave-RNN - Traveling Waves Encode the Recent Past and Enhance Sequence Learning
•
2304 - Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
Neurosymbolic
General
•
2501 - Developing a Foundation of Vector Symbolic Architectures Using Category Theory
•
2411 - Towards Learning to Reason: Comparing LLMs with Neurosymbolic on Arithmetic Relations in Abstract Reasoning
•
2411 - LogiCity- Advancing Neuro-Symbolic AI with Abstract Urban Simulation
•
2407 - Symbolic metaprogram search improves learning efficiency and explains rule learning in humans
•
2405 - Investigating Symbolic Capabilities of Large Language Models
•
2404 - AgentKit - Structured LLM Reasoning with Dynamic Graphs
•
2401 - A model of conceptual bootstrapping in human cognition
•
23xx - Neurosymbolic AI: the 3rd wave
•
2306 - Bayesian Program Learning by Decompiling Amortized Knowledge
•
2306 - From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought
•
2402 - WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
•
2107 - Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
•
2106 - DreamCoder: Bootstrapping Inductive Program Synthesis with Wake-Sleep Library Learning
Neural Program Synthesis / Induction
•
2405 - Learning to Reason via Program Generation, Emulation, and Search
•
2405 - Diffusion On Syntax Trees For Program Synthesis
•
2310 - Local Search and the Evolution of World Models
•
18xx - Neural Program Synthesis from Diverse Demonstration Videos
•
17xx - Program Synthesis
•
1512 - Human-Level Concept Learning Through Probabilistic Program Induction
•
13xx - Programs as Causal Models - Speculations on MentalPrograms and Mental Representation
Object-Centric
General
•
2503 - Unifying Causal and Object-Centric Representation Learning
•
2411 - Interaction Asymmetry - A General Principle For Learning Composable Abstractions
•
2408 - Zero-Shot Object-Centric Representation Learning
•
2406 - Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
•
2405 - Neural Language of Thought Models
•
2403 - Slot Abstractors: Toward Scalable Abstract Visual Reasoning
•
2312 - Reusable Slotwise Mechanisms
•
2310 - COSMOS - Neurosymbolic Grounding for Compositional World Models
•
2310 - Object-Centric Architectures Enable Efficient Causal Representation Learning
•
2307 - Compositional Generalization from First Principles
•
2205 - HOWM - Toward Compositional Generalization in Object-Oriented World Modeling (ICML22)
•
21xx - The Role of Disentanglement in Generalisation
NeuroCog
•
2304 - Solving the Binding Problem - Assemblies Form when Neurons Enhance Their Firing Rate—they Don’t Need to Oscillate or Synchronize
•
2109 - Capturing the Objects of Vision with Neural Networks
•
1805 - A New Approach to Solving the Feature Binding Problem in Primate Vision
Rotating Features & Complex-Value Synchrony
•
2410 - Artificial Kuramoto Oscillatory Neurons
•
2410 - Tracking Objects that Change in Appearance with Phase Synchrony
•
2405 - Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
•
23xx - Representing Part-Whole Hierarchy with Coordinated Synchrony in Neural Networks
•
2306 - Rotating Features for Object Discovery
•
2305 - Contrastive Training of Complex-Valued Autoencoders for Object Discovery
•
2204 - Complex-Valued Autoencoders for Object Discovery
•
1312 - Neuronal Synchrony in Complex-Valued Deep Networks
Planning & World Models & RL
Inbox
•
2310 - Skipper - Combining Spatial and Temporal Abstraction in Planning for Better Generalization [YB]
Position Papers
•
2405 - What is Lacking in Sora and V-JEPA's World Models? -A Philosophical Analysis of Video AIs Through the Theory of Productive Imagination
•
2403 - Are Video Generation Models World Simulators?
RL General
•
2401 - Closing the Gap between TD Learning and Supervised Learning--A Generalisation Point of View
Offline RL
•
2110 - Offline Reinforcement Learning with Implicit Q-Learning
World Representations
•
2404 - V-JEPA - Revisiting Feature Prediction for Learning Visual Representations from Video
•
2307 - IVCL - Does Visual Pretraining Help End-to-End Reasoning?
•
2206 - BYOL-Explore: Exploration by Bootstrapped Prediction
Diffuser Planning
•
2408 - Diffusion Model for Planning - A Systematic Literature Review
•
2408 - Diffusion Models Are Real-Time Game Engines
•
2407 - Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
•
2405 - Diffusion for World Modeling: Visual Details Matter in Atari
•
2405 - Hierarchical World Models as Visual Whole-Body Humanoid Controllers
•
2405 - PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
•
2404 - [Tutorial Blog] Diffusion Models for Video Generation (Lil’Log)
•
2403 - Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation
•
2402 - Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
•
2402 - DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
•
2401 - DiffuserLite - Towards Real-time Diffusion Planning
•
2401 - Simple Hierarchical Planning with Diffusion
•
2401 - Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View
•
2312 - SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution
•
2309 - Compositional Foundation Models for Hierarchical Planning
•
2309 - Reasoning with Latent Diffusion in Offline Reinforcement Learning
•
2306 - Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
•
2303 - Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
•
2302 - Learning Universal Policies via Text-Guided Video Generation
•
2209 - QDT - Q-learning Decision Transformer- Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
Dreamers & Dyna
•
2502 - : A Modular World Model over Streams of Tokens
•
2502 - Improving Transformer World Models for Data-Efficient RL
•
2407 - -IRIS: Efficient World Models with Context-Aware Tokenization
•
2406 - DART - Learning to Play Atari in a World of Tokens
•
2406 - A New View on Planning in Online Reinforcement Learning
•
2405 - CarDreamer: Open-source Learning Platform for World Model Based Autonomous Driving
•
2403 - Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization
MCTS
•
2406 - UniZero: Generalized and Efficient Planning with Scalable Latent World Models
Memory
•
2309 - Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
Applications
•
2405 - CarDreamer: Open-source Learning Platform for World Model Based Autonomous Driving
Benchmarks
•
2405 - AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
•
2402 - Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
Misc
•
PML Foundation
General
•
2402 - iDEM - Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
•
0312 - The IM Algorithm : A Variational Approach to Information Maximization
RL General
Unsupervised RL
•
2408 - Unsupervised-to-Online Reinforcement Learning
Safety & Alignment
Position
•
2502 - Superintelligent Agents Pose Catastrophic Risks- Can Scientist AI Offer a Safer Path?
•
2404 - Regulating Advanced Artificial Agents [Y. Bengio, Science]
•
24xx - Safeguarded AI: Constructing Guaranteed Safety v1.1
•
2310 - AI Alignment: A Comprehensive Survey [Peking University]
•
2309 - Anthropic's Responsible Scaling Policy
•
2309 - Provably Safe Systems: The Only Path to Controllable AGI
•
2306 - An Overview of Catastrophic AI Risks
•
2207 - Toward Verified Artificial Intelligence
•
2209 - The Alignment Problem from a Deep Learning Perspective
•
2112 - Eliciting latent knowledge: How to tell if your eyes deceive you
•
Alignment Forum https://www.alignmentforum.org/
LLM
•
2404 - BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
•
2404 - Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
•
2404 - Your Language Model is Secretly a Q-Function
•
2312 - Training Chain-Of-Thought via Latent-Variable Inference
•
•
2309 - Making Large Language Models Better Reasoners with Alignment
•
2304 - Bayesian Low-Rank Adaptation for Large Language Models [ICLR24]
•
2304 - Fundamental Limitations of Alignment in Large Language Models
•
2309 - Don’t Throw Away Your Value Model! Generating More Preferable Text with Value-Guided Monte-Carlo Tree Search Decoding
•
2205 - RL with KL Penalties is Better Viewed as Bayesian Inference
•
2202 - Red Teaming Language Models with Language Models
•
2111 - An Explanation of In-Context Learning as Implicit Bayesian Inference
Embodied Agent
•
Diffuser
•
2312 - Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model [NeurIPS’23]
•
2306 - Safe Planning with Diffusion Probabilistic Models
Safe Reinforcement Learning & Planning
•
2405 - Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
•
2402 - Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
•
2310 - Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
•
2307 - SafeDreamer: Safe Reinforcement Learning with World Models
•
2306 - Safe Planning with Diffusion Probabilistic Models
•
2306 - Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models
•
2304 - Approximate Shielding of Atari Agents for Safe Exploration
•
2101 - Shielding Atari Games with Bounded Prescience
Scientist AI
Truthness
•
2503 - Reasoning to Learn from Latent Thoughts
•
2503 - From Models to Microtheories- Distilling a Model's Topical Knowledge for Grounded Question-Answering
•
2402 - Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic
•
2307 - Measuring Faithfulness in Chain-of-Thought Reasoning
•
2305 - Language Models Don’t Always Say What They Think- Unfaithful Explanations in Chain-of-Thought Prompting
System 2 AI
Test-Time Compute & Training (TTC & TTT)
•
2501 - Test-time Computing: from System-1 Thinking to System-2 Thinking
•
◦
2406 - From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
•
2411 - The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
•
2408 - Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
•
2408 - Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
•
2404 - Stream of Search (SoS): Learning to Search in Language
•
2403 - Common 7B Language Models Already Possess Strong Math Capabilities
•
2312 - Training Chain-of-Thought via Latent-Variable Inference