{"total":106,"rows":[{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108,"area":null},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80,"area":null},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2309.09969","title":"Prompt a Robot to Walk with Large Language Models","created":"2023-09-18","cited_by_count":45,"area":null},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43,"area":null},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41,"area":null},{"id":"2312.11460","title":"Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response","created":"2023-12-18","cited_by_count":39,"area":null},{"id":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32,"area":null},{"id":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"area":null},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32,"area":null},{"id":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26,"area":null},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","cited_by_count":26,"area":null},{"id":"2405.05792","title":"RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation","created":"2024-05-09","cited_by_count":25,"area":null},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24,"area":null},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2409.20568","title":"Continuously Improving Mobile Manipulation with Autonomous Real-World RL","created":"2024-09-30","cited_by_count":22,"area":null},{"id":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21,"area":null},{"id":"2506.09995","title":"PlayerOne: Egocentric World Simulator","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19,"area":null},{"id":"2408.07147","title":"Controlling the World by Sleight of Hand","created":"2024-08-13","cited_by_count":19,"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":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2510.22161","title":"I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions","created":"2025-10-25","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2310.20608","title":"Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2302.05342","title":"Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL","created":"2023-02-10","cited_by_count":9,"area":null},{"id":"2306.08748","title":"Multi-Object Manipulation via Object-Centric Neural Scattering Functions","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2304.08663","title":"Continuous Versatile Jumping Using Learned Action Residuals","created":"2023-04-17","cited_by_count":8,"area":null},{"id":"2304.10888","title":"Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2305.16379","title":"Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2310.08809","title":"DexCatch: Learning to Catch Arbitrary Objects with Dexterous Hands","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2312.09906","title":"Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2403.16644","title":"Bridging the Sim-to-Real Gap with Bayesian Inference","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2305.12240","title":"Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics","created":"2023-05-20","cited_by_count":7,"area":null},{"id":"2306.03367","title":"Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction via Self-Supervision","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2306.12677","title":"SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer","created":"2023-06-22","cited_by_count":7,"area":null},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2409.09441","title":"PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion","created":"2024-09-14","cited_by_count":7,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2306.14601","title":"Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception","created":"2023-06-26","cited_by_count":5,"area":null},{"id":"2404.12378","title":"6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction","created":"2024-04-18","cited_by_count":5,"area":null},{"id":"2503.22444","title":"Scaling Laws in Scientific Discovery with AI and Robot Scientists","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2310.10372","title":"Learning Object Permanence from Videos via Latent Imaginations","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2405.03865","title":"Information-driven Affordance Discovery for Efficient Robotic Manipulation","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2209.08033","title":"Learning Policies for Continuous Control via Transition Models","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"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":"2307.11954","title":"On-Robot Bayesian Reinforcement Learning for POMDPs","created":"2023-07-22","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":"2602.12373","title":"Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.16085","title":"Interact3D: Compositional 3D Generation of Interactive Objects","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2304.11104","title":"Approximate Shielding of Atari Agents for Safe Exploration","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2304.12080","title":"Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2306.01205","title":"SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2407.03652","title":"Over the Edge of Chaos? Excess Complexity as a Roadblock to Artificial General Intelligence","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2506.16216","title":"From Pixels to CSI: Distilling Latent Dynamics For Efficient Wireless Resource Management","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2605.25346","title":"Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.21406","title":"Robot Self-Improvement via Human-Video Dynamics Models","created":"2026-06-19","cited_by_count":2,"area":null},{"id":"2209.07171","title":"Learning to Exploit Elastic Actuators for Quadruped Locomotion","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2310.01767","title":"Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2311.18773","title":"Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2408.16875","title":"Learning Multi-agent Multi-machine Tending by Mobile Robots","created":"2024-08-29","cited_by_count":1,"area":null},{"id":"2410.17882","title":"Identifiable Representation and Model Learning for Latent Dynamic Systems","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2504.06468","title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2508.03218","title":"ActionSink: Toward Precise Robot Manipulation with Dynamic Integration of Action Flow","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.08312","title":"Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2606.15015","title":"NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.17394","title":"Damage Adaptation in Seconds for Architected Materials","created":"2026-06-16","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":"2311.06828","title":"Towards Continual Reinforcement Learning for Quadruped Robots","created":"2023-11-12","cited_by_count":0,"area":null},{"id":"2409.11600","title":"No Saved Kaleidosope: an 100% Jitted Neural Network Coding Language with Pythonic Syntax","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2410.19761","title":"Physical Simulation for Multi-agent Multi-machine Tending","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2503.13814","title":"FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2505.06744","title":"LineFlow: A Framework to Learn Active Control of Production Lines","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2506.01350","title":"Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2508.19172","title":"From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2603.21853","title":"Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.29315","title":"IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.12933","title":"DINO-Explorer: Active Underwater Discovery via Ego-Motion Compensated Semantic Predictive Coding","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.21456","title":"Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.02027","title":"World-Task Factorization for Robot Learning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.14585","title":"Sensitivity Shaping for Latent Modeling","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.22999","title":"WCM: World-Cognition Model for Generalizable Human-Robot Interaction","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.09627","title":"Seven Sources of Physical AI Capability Formation","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":"100"}