{"total":61,"rows":[{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522,"area":null},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2306.17525","title":"MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems","created":"2023-06-30","cited_by_count":29,"area":null},{"id":"2303.13002","title":"Planning Goals for Exploration","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2507.08800","title":"NeuralOS: Towards Simulating Operating Systems via Neural Generative Models","created":"2025-07-11","cited_by_count":19,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2305.04934","title":"Generative Pretrained Autoregressive Transformer Graph Neural Network applied to the Analysis and Discovery of Novel Proteins","created":"2023-05-07","cited_by_count":10,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2308.12252","title":"How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy","created":"2023-08-23","cited_by_count":8,"area":null},{"id":"2408.14915","title":"Can Transformers Do Enumerative Geometry?","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2506.09272","title":"G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2410.13331","title":"Improving Discrete Optimisation Via Decoupled Straight-Through Estimator","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2509.01728","title":"Constrained Decoding for Safe Robot Navigation Foundation Models","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2501.12670","title":"Celo: Training Versatile Learned Optimizers on a Compute Diet","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2506.19055","title":"Xray2Xray: World Model from Chest X-rays with Volumetric Context","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2303.04212","title":"ConBaT: Control Barrier Transformer for Safe Policy Learning","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2410.01458","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2502.11377","title":"PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2308.04263","title":"BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning","created":"2023-08-08","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2404.05440","title":"Tree Search-Based Policy Optimization under Stochastic Execution Delay","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2412.10599","title":"Advances in Transformers for Robotic Applications: A Review","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2508.21449","title":"Learning Lifted Action Models From Traces of Incomplete Actions and States","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2511.14918","title":"X-WIN: Building Chest Radiograph World Model via Predictive Sensing","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2605.12167","title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2609.04200","title":"Principia: Relational Physics Tests for Video Models","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2212.11353","title":"Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2506.16912","title":"From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2310.16655","title":"Towards Control-Centric Representations in Reinforcement Learning from Images","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2404.11576","title":"State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2410.17428","title":"Uncovering RL Integration in SSL Loss: Objective-Specific Implications for Data-Efficient RL","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2602.04557","title":"Textual Planning with Explicit Latent Transitions","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.22227","title":"A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.13282","title":"Differentiable Learning of Lifted Action Schemas for Classical Planning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2609.36227","title":"One-Step Next-Latent Prediction Is Not a World Model","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38383","title":"Learning to Plan from Random Exploration","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40129","title":"VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03812","title":"Least Squares for Time Series Forecasting","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}