{"total":56,"rows":[{"id":"2510.00739","title":"TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning","created":"2025-10-01","cited_by_count":22,"area":"deeprl"},{"id":"2509.14353","title":"DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion","created":"2025-09-17","cited_by_count":15,"area":"diffusion"},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2505.23058","title":"Be.FM: Open Foundation Models for Human Behavior","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","cited_by_count":8,"area":"deeprl"},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2602.19634","title":"Compositional Planning with Jumpy World Models","created":"2026-02-23","cited_by_count":7,"area":"wm"},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2512.24321","title":"UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots","created":"2025-12-30","cited_by_count":5,"area":null},{"id":"2601.19707","title":"Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow","created":"2026-01-27","cited_by_count":5,"area":"deeprl"},{"id":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2603.07516","title":"InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2507.05906","title":"Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why","created":"2025-07-08","cited_by_count":2,"area":"offlinerl"},{"id":"2509.20927","title":"SimDiff: Simulator-constrained Diffusion Model for Physically Plausible Motion Generation","created":"2025-09-25","cited_by_count":2,"area":"diffusion"},{"id":"2510.06203","title":"Reference Grounded Skill Discovery","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2607.15163","title":"Scaling Behavior Foundation Model for Humanoid Robots","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2509.26605","title":"Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning","created":"2025-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2602.07730","title":"The Laplacian Keyboard: Beyond the Linear Span","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.21599","title":"Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2602.23205","title":"EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.25464","title":"Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning","created":"2026-03-26","cited_by_count":1,"area":"deeprl"},{"id":"2604.05112","title":"Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner","created":"2026-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2604.25496","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","created":"2026-04-28","cited_by_count":1,"area":"offlinerl"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.03497","title":"BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2509.19023","title":"Reduced-Order Model-Guided Reinforcement Learning for Demonstration-Free Humanoid Locomotion","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2601.04441","title":"Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization","created":"2026-01-07","cited_by_count":0,"area":"offlinerl"},{"id":"2601.22823","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","created":"2026-01-30","cited_by_count":0,"area":"offlinerl"},{"id":"2602.00403","title":"DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2603.20103","title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.18064","title":"Towards Human Motion World Models via Executable Behaviour Representations","created":"2026-04-20","cited_by_count":0,"area":"wm"},{"id":"2605.13207","title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.21707","title":"Zero-shot adaptation to order book dynamics","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.29906","title":"Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.14433","title":"Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motions","created":"2026-06-12","cited_by_count":0,"area":"offlinerl"},{"id":"2606.16696","title":"VENOM: Versatile Embodied Network for Omni-bodied Motion tracking","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.20705","title":"MotionPyramid: Hierarchical Motion Representation and Residual Interfaces","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.21271","title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2608.11769","title":"Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence","created":"2026-08-12","cited_by_count":0,"area":"vla"},{"id":"2609.18111","title":"A Comprehensive Review of Generative Physical Artificial Intelligence","created":"2026-09-16","cited_by_count":0,"area":"diffusion"},{"id":"2609.35615","title":"Behavioral Foundation Models for Quality Diversity","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37677","title":"Learning Expressive and Compositional Motion Representation via Spectral Skills","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02196","title":"InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05350","title":"Task Inference Beyond Least Squares in Behavioral Foundation Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19883","title":"Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}