{"total":104,"rows":[{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248,"area":null},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245,"area":null},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179,"area":null},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161,"area":null},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153,"area":null},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119,"area":null},{"id":"2107.04004","title":"3D Neural Scene Representations for Visuomotor Control","created":"2021-07-08","cited_by_count":111,"area":null},{"id":"2104.02646","title":"gradSim: Differentiable simulation for system identification and visuomotor control","created":"2021-04-06","cited_by_count":100,"area":null},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95,"area":null},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2109.05668","title":"UMPNet: Universal Manipulation Policy Network for Articulated Objects","created":"2021-09-13","cited_by_count":65,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54,"area":null},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54,"area":null},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51,"area":null},{"id":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","cited_by_count":49,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47,"area":null},{"id":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46,"area":null},{"id":"2105.01060","title":"Curious Representation Learning for Embodied Intelligence","created":"2021-05-03","cited_by_count":44,"area":null},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2210.06876","title":"Learning Physical Dynamics with Subequivariant Graph Neural Networks","created":"2022-10-13","cited_by_count":39,"area":null},{"id":"2204.02393","title":"Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining","created":"2022-04-05","cited_by_count":37,"area":null},{"id":"2107.13545","title":"Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation","created":"2021-07-28","cited_by_count":35,"area":null},{"id":"2309.12300","title":"See to Touch: Learning Tactile Dexterity through Visual Incentives","created":"2023-09-21","cited_by_count":35,"area":null},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2107.12931","title":"Autonomous Reinforcement Learning via Subgoal Curricula","created":"2021-07-27","cited_by_count":33,"area":null},{"id":"2407.20635","title":"Autonomous Improvement of Instruction Following Skills via Foundation Models","created":"2024-07-30","cited_by_count":32,"area":null},{"id":"2108.13035","title":"SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning","created":"2021-08-30","cited_by_count":31,"area":null},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2101.11812","title":"SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation","created":"2021-01-28","cited_by_count":24,"area":null},{"id":"2106.00671","title":"What Can I Do Here? Learning New Skills by Imagining Visual Affordances","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20,"area":null},{"id":"2103.09439","title":"HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2107.05627","title":"Hierarchical Neural Dynamic Policies","created":"2021-07-12","cited_by_count":17,"area":null},{"id":"2104.14040","title":"Pushing it out of the Way: Interactive Visual Navigation","created":"2021-04-28","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":"2405.17879","title":"Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2508.13013","title":"EgoTwin: Dreaming Body and View in First Person","created":"2025-08-18","cited_by_count":13,"area":null},{"id":"2203.01810","title":"Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2304.11470","title":"3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes","created":"2023-04-22","cited_by_count":12,"area":null},{"id":"2501.05673","title":"Network Diffuser for Placing-Scheduling Service Function Chains with Inverse Demonstration","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2107.13668","title":"Discovering User-Interpretable Capabilities of Black-Box Planning Agents","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2203.11176","title":"One After Another: Learning Incremental Skills for a Changing World","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2209.08996","title":"EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2407.06704","title":"Self-supervised visual learning from interactions with objects","created":"2024-07-09","cited_by_count":10,"area":null},{"id":"2109.10024","title":"Self-Supervised Action-Space Prediction for Automated Driving","created":"2021-09-21","cited_by_count":9,"area":null},{"id":"2112.05298","title":"IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes","created":"2021-12-10","cited_by_count":9,"area":null},{"id":"2204.13695","title":"Bilinear value networks","created":"2022-04-28","cited_by_count":9,"area":null},{"id":"2105.04607","title":"Efficient Self-Supervised Data Collection for Offline Robot Learning","created":"2021-05-10","cited_by_count":8,"area":null},{"id":"2207.00052","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","created":"2022-06-30","cited_by_count":8,"area":null},{"id":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","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":"2407.08585","title":"HACMan++: Spatially-Grounded Motion Primitives for Manipulation","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2501.13457","title":"Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks","created":"2025-01-23","cited_by_count":6,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2102.02100","title":"Object and Relation Centric Representations for Push Effect Prediction","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2109.13859","title":"NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2212.04581","title":"PALMER: Perception-Action Loop with Memory for Long-Horizon Planning","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2302.13375","title":"Perceiving Unseen 3D Objects by Poking the Objects","created":"2023-02-26","cited_by_count":5,"area":null},{"id":"2110.06912","title":"OPEn: An Open-ended Physics Environment for Learning Without a Task","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2306.10190","title":"ALP: Action-Aware Embodied Learning for Perception","created":"2023-06-16","cited_by_count":4,"area":null},{"id":"2409.03107","title":"RoboKoop: Efficient Control Conditioned Representations from Visual Input in Robotics using Koopman Operator","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2110.12352","title":"DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation with Differentiable Simulator","created":"2021-10-24","cited_by_count":3,"area":null},{"id":"2209.09115","title":"Compositional Law Parsing with Latent Random Functions","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2211.06134","title":"Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2304.04446","title":"Inferring Fluid Dynamics via Inverse Rendering","created":"2023-04-10","cited_by_count":3,"area":null},{"id":"2307.03175","title":"Push Past Green: Learning to Look Behind Plant Foliage by Moving It","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2402.19405","title":"Navigating Hallucinations for Reasoning of Unintentional Activities","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2504.00707","title":"Interleaved Multitask Learning with Energy Modulated Learning Progress","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2512.20052","title":"Learning Skills from Action-Free Videos","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2101.10384","title":"droidlet: modular, heterogenous, multi-modal agents","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2102.02493","title":"Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models","created":"2021-02-04","cited_by_count":2,"area":null},{"id":"2110.10255","title":"A Simple Approach to Continual Learning by Transferring Skill Parameters","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2111.05318","title":"A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation","created":"2021-11-09","cited_by_count":2,"area":null},{"id":"2208.08962","title":"Stable Object Reorientation using Contact Plane Registration","created":"2022-08-18","cited_by_count":2,"area":null},{"id":"2310.04617","title":"SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2103.11881","title":"Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2107.09047","title":"Know Thyself: Transferable Visual Control Policies Through Robot-Awareness","created":"2021-07-19","cited_by_count":1,"area":null},{"id":"2202.09006","title":"KINet: Unsupervised Forward Models for Robotic Pushing Manipulation","created":"2022-02-18","cited_by_count":1,"area":null},{"id":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2104.01980","title":"Probabilistic Programming Bots in Intuitive Physics Game Play","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2105.01061","title":"Collision Replay: What Does Bumping Into Things Tell You About Scene Geometry?","created":"2021-05-03","cited_by_count":0,"area":null},{"id":"2111.07986","title":"Nonprehensile Riemannian Motion Predictive Control","created":"2021-11-15","cited_by_count":0,"area":null}],"next_cursor":"100"}