AGI
•
2406 - Open-Endedness is Essential for Artificial Superhuman Intelligence
•
2311 - Levels of AGI: Operationalizing Progress on the Path to AGI
AI Mathematician
Autoformalization
•
2406 - AI-Assisted Generation of Difficult Math Questions
•
2403 - Don’t Trust: Verify – Grounding LLM Quantitative Reasoning with Autoformalization
•
2403 - Machine Learning and Information Theory Concepts Towards an AI Mathematician [Y. Bengio]
•
2310 - A New Approach Towards Autoformalization
•
2212 - Solving Quantitative Reasoning Problems with Language Models
•
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
Automated Theorem Proving
•
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
Interactive Embodied 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
•
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
•
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
Compositional Representation
Position Papers
•
2402 - Compositional Generative Modeling - A Single Model is Not All You Need
General
•
2407 - Deciphering the Role of Representation Disentanglement- Investigating Compositional Generalization in CLIP Models
•
2406 - Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
•
The Compositionality of Neural Networks: Integrating Symbolism and Connectionism
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
Object-Centric
•
2405 - Neural Language of Thought Models
•
2312 - Reusable Slotwise Mechanisms
•
2310 - Object-Centric Architectures Enable Efficient Causal Representation Learning
•
2205 - HOWM - Toward Compositional Generalization in Object-Oriented World Modeling (ICML22)
•
21xx - The Role of Disentanglement in Generalisation
Emergent Communication
•
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
Causal Representations
Position & Survey Papers
•
2403 - Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
•
2402 - Essential Role of Causality in Foundation World Models for Embodied AI
•
2105 - Toward Causal Representation Learning
Foundational
•
2407 - Disentangled Representations for Causal Cognition
•
2406 - The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning
•
2305 - Interventional Causal Representation Learning
•
2310 - Towards Causal Foundation Model: on Duality between Causal Inference and Attention
•
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
Discovery
•
2405 - Demystifying Amortized Causal Discovery with Transformers
•
2402 - Efficient Causal Graph Discovery Using Large Language Models
•
2204 - Learning to Induce Causal Structure
Benchmarks
•
2405 - Smoke and Mirrors in Causal Downstream Tasks
Causality in NeuroCog
•
2406 - Counterfactual Simulation in Causal Cognition (by Tobias Gerstenberg)
•
2405 - The Development of Human Causal Learning and Reasoning
Causal World Model & Agent
•
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
•
2200 - CausalDyna: Improving Generalization of Dyna-Style Reinforcement Learning via Counterfactual-Based Data Augmentation
•
2100 - Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Planning & World Models
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?
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
•
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
•
2309 - Compositional Foundation Models for Hierarchical Planning
•
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
•
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
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
Memory
•
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
•
2112 - Relating Transformers to Models and Neural Representations of The Hippocampal Formation [J. Whittington]
NeuroCog
•
2306 - Organizing memories for generalization in complementary learning systems
Exploration
•
2206 - BYOL-Explore: Exploration by Bootstrapped Prediction
Safety & Alignment
Position
•
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
•
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
General Backbone Architectures
•
2406 - Vision-LSTM: xLSTM as Generic Vision Backbone
•
2405 - Aaren - Attention as an RNN
2212 - DiT - Scalable Diffusion Models with Transformers
•
2202 - GroupViT: Semantic Segmentation Emerges from Text Supervision
•
2202 - MaskGIT: Masked Generative Image Transformer
GFlowNets
•
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
•
2209 - Learning GFlowNets from Partial Episodes for Improved Convergence and Stability
Diffusion Models
Flow Matching
•
2406 - Variational Flow Matching for Graph Generation
•
2312 - Boosting Latent Diffusion with Flow Matching
•
2307 - Flow Matching in Latent Space
•
2211 - Efficient Video Prediction via Sparsely Conditioned Flow Matching
•
2210 - Flow Matching for Generative Modeling
Protein Design
Position Papers
•
2402 - Generative AI for Controllable Protein Sequence Design: A Survey
LLM General
Position Papers
•
2402 - Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
Reasoning
•
2406 - Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
•
2405 - Understanding Transformer Reasoning Capabilities via Graph Algorithms
•
2405 - From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
•
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
•
2308 - Graph of Thoughts - Solving Elaborate Problems with Large Language Models
•
2212 - Prompting Is Programming- A Query Language for 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
Conscious Information Processing
NeuroCog
•
2407 - Conscious Artificial Intelligence and Biological Naturalism
•
2407 - What Does Decoding from The PFC Reveal About Consciousness? [Ned Block]