{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2409.00588","title":"Diffusion Policy Policy Optimization","created":"2024-09-01","cited_by_count":280},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145},{"id":"2312.11752","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","created":"2023-12-18","cited_by_count":138},{"id":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136},{"id":"2505.03233","title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","created":"2025-05-06","cited_by_count":123},{"id":"2311.00899","title":"RoboVQA: Multimodal Long-Horizon Reasoning for Robotics","created":"2023-11-01","cited_by_count":120},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101},{"id":"2309.16984","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","created":"2023-09-29","cited_by_count":100},{"id":"2411.04549","title":"Vision Language Models are In-Context Value Learners","created":"2024-11-07","cited_by_count":90},{"id":"2401.08553","title":"FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning","created":"2024-01-16","cited_by_count":80},{"id":"2503.04975","title":"Energy-Weighted Flow Matching for Offline Reinforcement Learning","created":"2025-03-06","cited_by_count":73},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63},{"id":"2505.12224","title":"RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction","created":"2025-05-18","cited_by_count":41},{"id":"2506.12811","title":"Flow-Based Policy for Online Reinforcement Learning","created":"2025-06-15","cited_by_count":37},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32},{"id":"2407.20635","title":"Autonomous Improvement of Instruction Following Skills via Foundation Models","created":"2024-07-30","cited_by_count":32},{"id":"2401.14403","title":"Adaptive Mobile Manipulation for Articulated Objects In the Open World","created":"2024-01-25","cited_by_count":31},{"id":"2302.06604","title":"ALAN: Autonomously Exploring Robotic Agents in the Real World","created":"2023-02-13","cited_by_count":24},{"id":"2310.17634","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","created":"2023-10-26","cited_by_count":24},{"id":"2212.09902","title":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","created":"2022-12-19","cited_by_count":23},{"id":"2402.15025","title":"Practice Makes Perfect: Planning to Learn Skill Parameter Policies","created":"2024-02-22","cited_by_count":23},{"id":"2409.20568","title":"Continuously Improving Mobile Manipulation with Autonomous Real-World RL","created":"2024-09-30","cited_by_count":22},{"id":"2305.03270","title":"Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators","created":"2023-05-05","cited_by_count":21},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20},{"id":"2405.18187","title":"AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization","created":"2024-05-28","cited_by_count":19},{"id":"2309.03322","title":"REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation","created":"2023-09-06","cited_by_count":15},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9},{"id":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8},{"id":"2401.00006","title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation","created":"2023-12-12","cited_by_count":6},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3}],"next_cursor":null}