{"list":"other","total":52,"rows":[{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"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":"2510.10274","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","created":"2025-10-11","cited_by_count":303},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205},{"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":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2512.15692","title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","created":"2025-12-17","cited_by_count":142},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2508.00795","title":"Video Generators are Robot Policies","created":"2025-08-01","cited_by_count":92},{"id":"2511.17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","created":"2025-11-21","cited_by_count":78},{"id":"2603.10448","title":"DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control","created":"2026-03-11","cited_by_count":76},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70},{"id":"2507.12898","title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation","created":"2025-07-17","cited_by_count":62},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"2602.12215","title":"LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion","created":"2026-02-12","cited_by_count":52},{"id":"2511.16651","title":"InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy","created":"2025-11-20","cited_by_count":50},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50},{"id":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36},{"id":"2505.15660","title":"Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization","created":"2025-05-21","cited_by_count":33},{"id":"2511.15704","title":"In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data","created":"2025-11-19","cited_by_count":26},{"id":"2607.06403","title":"From Foundation to Application: Improving VLA Models in Practice","created":"2026-07-07","cited_by_count":26},{"id":"2502.16587","title":"Human2Robot: Learning Robot Actions from Paired Human-Robot Videos","created":"2025-02-23","cited_by_count":25},{"id":"2406.14235","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","created":"2024-06-20","cited_by_count":23},{"id":"2501.14208","title":"You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations","created":"2025-01-24","cited_by_count":21},{"id":"2602.10106","title":"EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration","created":"2026-02-10","cited_by_count":21},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19},{"id":"2606.11187","title":"Next Forcing: Causal World Modeling with Multi-Chunk Prediction","created":"2026-06-09","cited_by_count":18},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16},{"id":"2606.19333","title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","created":"2026-06-17","cited_by_count":13},{"id":"2605.30877","title":"Wall-OSS-0.5 Technical Report","created":"2026-05-29","cited_by_count":12},{"id":"2608.02580","title":"Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data","created":"2026-08-03","cited_by_count":11},{"id":"2607.27205","title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","created":"2026-07-29","cited_by_count":10},{"id":"2606.30457","title":"What Enables In-Context Behavior Prompting for Manipulation?","created":"2026-06-29","cited_by_count":7},{"id":"2607.20033","title":"HOST:Robots Acquire Manipulation Skills in Seconds from a Single Human Video","created":"2026-07-22","cited_by_count":7},{"id":"2607.24159","title":"DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning","created":"2026-07-27","cited_by_count":4},{"id":"2509.22205","title":"From Watch to Imagine: Steering Long-horizon Manipulation via Human Demonstration and Future Envisionment","created":"2025-09-26","cited_by_count":2}],"next_cursor":null}