{"list":"other","total":70,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"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":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"1912.04443","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","created":"2019-12-10","cited_by_count":105},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"2503.00779","title":"Phantom: Training Robots Without Robots Using Only Human Videos","created":"2025-03-02","cited_by_count":70},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2405.02292","title":"ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation","created":"2024-02-07","cited_by_count":63},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57},{"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":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48},{"id":"2502.20391","title":"Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation","created":"2025-02-27","cited_by_count":47},{"id":"2508.09976","title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","created":"2025-08-13","cited_by_count":43},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40},{"id":"2411.00965","title":"SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation","created":"2024-11-01","cited_by_count":38},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38},{"id":"2505.08787","title":"UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations","created":"2025-05-13","cited_by_count":35},{"id":"2310.16917","title":"MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation","created":"2023-10-25","cited_by_count":34},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32},{"id":"2509.19626","title":"EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data","created":"2025-09-23","cited_by_count":29},{"id":"2505.11920","title":"H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos","created":"2025-05-17","cited_by_count":23},{"id":"2601.05573","title":"Orient Anything V2: Unifying Orientation and Rotation Understanding","created":"2026-01-09","cited_by_count":23},{"id":"2509.04443","title":"EMMA: Scaling Mobile Manipulation via Egocentric Human Data","created":"2025-09-04","cited_by_count":21},{"id":"2509.09769","title":"MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos","created":"2025-09-11","cited_by_count":20},{"id":"2509.10952","title":"ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation","created":"2025-09-13","cited_by_count":20},{"id":"2506.20668","title":"DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy","created":"2025-06-25","cited_by_count":19},{"id":"2511.16661","title":"Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations","created":"2025-11-20","cited_by_count":19},{"id":"2511.21690","title":"TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos","created":"2025-11-26","cited_by_count":15},{"id":"2506.04227","title":"Object-centric 3D Motion Field for Robot Learning from Human Videos","created":"2025-06-04","cited_by_count":14},{"id":"2603.22264","title":"UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos","created":"2026-03-23","cited_by_count":14},{"id":"2602.09013","title":"Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction","created":"2026-02-09","cited_by_count":11},{"id":"2508.11049","title":"GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning","created":"2025-08-14","cited_by_count":9},{"id":"2604.08534","title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","created":"2026-04-09","cited_by_count":8},{"id":"2510.01433","title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","created":"2025-10-01","cited_by_count":3},{"id":"2603.20850","title":"Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves","created":"2026-03-21","cited_by_count":3},{"id":"2510.03706","title":"EmbodiSwap for Zero-Shot Robot Imitation Learning","created":"2025-10-04","cited_by_count":2}],"next_cursor":null}