{"total":208,"rows":[{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175,"area":"offlinerl"},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129,"area":null},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101,"area":null},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58,"area":null},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57,"area":null},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48,"area":null},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46,"area":null},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42,"area":"vla"},{"id":"2402.13349","title":"Aria Everyday Activities Dataset","created":"2024-02-20","cited_by_count":39,"area":null},{"id":"2405.04378","title":"Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting","created":"2024-05-07","cited_by_count":38,"area":null},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33,"area":null},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32,"area":null},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29,"area":null},{"id":"2509.19626","title":"EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data","created":"2025-09-23","cited_by_count":29,"area":"offlinerl"},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28,"area":"mllm"},{"id":"2409.13426","title":"HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device","created":"2024-09-20","cited_by_count":27,"area":null},{"id":"2405.04812","title":"General Place Recognition Survey: Towards Real-World Autonomy","created":"2024-05-08","cited_by_count":23,"area":null},{"id":"2406.19811","title":"EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":23,"area":null},{"id":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22,"area":null},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2601.18157","title":"Agentic Very Long Video Understanding","created":"2026-01-26","cited_by_count":20,"area":"agents"},{"id":"2607.08436","title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","created":"2026-07-08","cited_by_count":20,"area":"wm"},{"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,"area":null},{"id":"2407.06628","title":"Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition","created":"2024-07-09","cited_by_count":18,"area":null},{"id":"2512.17907","title":"Dexterous World Models","created":"2025-12-19","cited_by_count":18,"area":"wm"},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17,"area":null},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17,"area":null},{"id":"2401.17217","title":"GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear","created":"2024-01-30","cited_by_count":16,"area":"mllm"},{"id":"2504.08654","title":"The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation","created":"2025-04-11","cited_by_count":16,"area":null},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16,"area":null},{"id":"2405.19917","title":"Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition","created":"2024-05-30","cited_by_count":14,"area":"distill"},{"id":"2504.04956","title":"REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning","created":"2025-04-07","cited_by_count":14,"area":"diffusion"},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2408.17168","title":"EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs","created":"2024-08-30","cited_by_count":13,"area":null},{"id":"2503.19355","title":"ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models","created":"2025-03-25","cited_by_count":13,"area":"lr"},{"id":"2507.21378","title":"ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Modal Wearable Devices","created":"2025-07-28","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":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2502.20879","title":"egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2509.21986","title":"Developing Vision-Language-Action Model from Egocentric Videos","created":"2025-09-26","cited_by_count":11,"area":"vla"},{"id":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10,"area":null},{"id":"2506.07155","title":"GoTrack: Generic 6DoF Object Pose Refinement and Tracking","created":"2025-06-08","cited_by_count":10,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2508.00088","title":"The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2508.14466","title":"LookOut: Real-World Humanoid Egocentric Navigation","created":"2025-08-20","cited_by_count":9,"area":null},{"id":"2504.18424","title":"LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning","created":"2025-04-25","cited_by_count":8,"area":null},{"id":"2510.22443","title":"Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents","created":"2025-10-25","cited_by_count":8,"area":"mllm"},{"id":"2512.16907","title":"Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2602.22209","title":"WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2605.30282","title":"Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation","created":"2026-05-28","cited_by_count":8,"area":"vla"},{"id":"2502.20389","title":"From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2504.13060","title":"Imaging for All-Day Wearable Smart Glasses","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2509.09154","title":"Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective","created":"2025-09-11","cited_by_count":7,"area":"lr"},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2404.09254","title":"TEXT2TASTE: A Versatile Egocentric Vision System for Intelligent Reading Assistance Using Large Language Model","created":"2024-04-14","cited_by_count":6,"area":null},{"id":"2404.14409","title":"CrossScore: Towards Multi-View Image Evaluation and Scoring","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2505.08665","title":"SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation","created":"2025-05-13","cited_by_count":6,"area":null},{"id":"2505.24848","title":"Reading Recognition in the Wild","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2603.28732","title":"Pandora: Articulated 3D Scene Graphs from Egocentric Vision","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2603.28896","title":"Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2604.03486","title":"VisionClaw: Always-On AI Agents through Smart Glasses","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2408.03160","title":"User-in-the-loop Evaluation of Multimodal LLMs for Activity Assistance","created":"2024-08-04","cited_by_count":5,"area":"lr"},{"id":"2409.07365","title":"Event-based Mosaicing Bundle Adjustment","created":"2024-09-11","cited_by_count":5,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2510.22129","title":"egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks","created":"2025-10-25","cited_by_count":5,"area":null},{"id":"2606.17054","title":"Human Universal Grasping","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2606.22174","title":"OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation","created":"2026-06-20","cited_by_count":5,"area":"vla"},{"id":"2311.06455","title":"Aria-NeRF: Multimodal Egocentric View Synthesis","created":"2023-11-11","cited_by_count":4,"area":null},{"id":"2410.04419","title":"LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation","created":"2024-10-06","cited_by_count":4,"area":null},{"id":"2503.11806","title":"Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2509.26278","title":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2512.13238","title":"Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2602.05321","title":"Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2603.15847","title":"FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2603.28760","title":"SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild","created":"2026-03-30","cited_by_count":4,"area":null},{"id":"2504.17735","title":"EgoCHARM: Resource-Efficient Hierarchical Activity Recognition using an Egocentric IMU Sensor","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2505.24389","title":"Leadership Assessment in Pediatric Intensive Care Unit Team Training","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.07860","title":"Egocentric Event-Based Vision for Ping Pong Ball Trajectory Prediction","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2506.14973","title":"Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2511.17581","title":"EgoCogNav: Cognition-aware Human Egocentric Navigation","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2602.00793","title":"SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2603.01104","title":"Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI","created":"2026-03-01","cited_by_count":3,"area":"agents"},{"id":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3,"area":null}],"next_cursor":"100"}