{"list":"other","total":72,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"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":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2404.09990","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","created":"2024-04-15","cited_by_count":193},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2307.04577","title":"AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System","created":"2023-07-10","cited_by_count":152},{"id":"2509.23951","title":"HunyuanImage 3.0 Technical Report","created":"2025-09-28","cited_by_count":149},{"id":"2411.07199","title":"OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision","created":"2024-11-11","cited_by_count":145},{"id":"2602.06949","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","created":"2026-02-06","cited_by_count":135},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"2405.04007","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","created":"2024-05-07","cited_by_count":97},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82},{"id":"2407.03162","title":"Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning","created":"2024-07-03","cited_by_count":77},{"id":"2407.10353","title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","created":"2024-07-14","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":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67},{"id":"2305.05706","title":"DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects","created":"2023-05-09","cited_by_count":66},{"id":"2505.21864","title":"DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation","created":"2025-05-28","cited_by_count":66},{"id":"2207.01322","title":"Harmonizer: Learning to Perform White-Box Image and Video Harmonization","created":"2022-07-04","cited_by_count":61},{"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":"2508.09976","title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","created":"2025-08-13","cited_by_count":43},{"id":"2409.19499","title":"FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset","created":"2024-09-29","cited_by_count":40},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29},{"id":"2502.16587","title":"Human2Robot: Learning Robot Actions from Paired Human-Robot Videos","created":"2025-02-23","cited_by_count":25},{"id":"2509.22199","title":"MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training","created":"2025-09-26","cited_by_count":25},{"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":"2602.10106","title":"EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration","created":"2026-02-10","cited_by_count":21},{"id":"2604.23570","title":"EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks","created":"2026-04-26","cited_by_count":20},{"id":"2512.17907","title":"Dexterous World Models","created":"2025-12-19","cited_by_count":18},{"id":"2503.00774","title":"Shadow: Leveraging Segmentation Masks for Cross-Embodiment Policy Transfer","created":"2025-03-02","cited_by_count":14},{"id":"2509.14688","title":"exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation","created":"2025-09-18","cited_by_count":14},{"id":"2512.17253","title":"Mitty: Diffusion-based Human-to-Robot Video Generation","created":"2025-12-19","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":"2509.05513","title":"OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation","created":"2025-09-05","cited_by_count":13},{"id":"2510.08022","title":"FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset","created":"2025-10-09","cited_by_count":11},{"id":"2512.09406","title":"H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos","created":"2025-12-10","cited_by_count":9},{"id":"2506.23152","title":"DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover","created":"2025-06-29","cited_by_count":8},{"id":"2512.06065","title":"EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing","created":"2025-12-05","cited_by_count":8},{"id":"2512.10284","title":"MotionEdit: Benchmarking and Learning Motion-Centric Image Editing","created":"2025-12-11","cited_by_count":7},{"id":"2507.03930","title":"RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot","created":"2025-07-05","cited_by_count":2},{"id":"2512.15411","title":"MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training","created":"2025-12-17","cited_by_count":2}],"next_cursor":null}