mlsanityData to 7 Oct 2026

EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos

arXiv 2507.12440 ↗First posted 16 Jul 2025cs.RO cs.AI cs.CVcited by 116

On the map: Vision-language-action models → Human-video and latent-action pretraining

also in 1 more
Abstract (arXiv)

Real robot data collection for imitation learning has led to significant advancements in robotic manipulation. However, the requirement for robot hardware in the process fundamentally constrains the scale of the data. In this paper, we explore training Vision-Language-Action (VLA) models using egocentric human videos. The benefit of using human videos is not only for their scale but more importantly for the richness of scenes and tasks. With a VLA trained on human video that predicts human wrist and hand actions, we can perform Inverse Kinematics and retargeting to convert the human actions to robot actions. We fine-tune the model using a few robot manipulation demonstrations to obtain the robot policy, namely EgoVLA. We propose a simulation benchmark called Ego Humanoid Manipulation Benchmark, where we design diverse bimanual manipulation tasks with demonstrations. We fine-tune and evaluate EgoVLA with Ego Humanoid Manipulation Benchmark and show significant improvements over baselines and ablate the importance of human data. Videos can be found on our website: https://rchalyang.github.io/EgoVLA

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models. Builds on 55 of its 74 references that are in the map. First posted on arXiv 16 Jul 2025.

Builds on

55 of 74 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Latent Action Pretraining from Videos15 Oct

Other references · 54

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  5. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  6. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  7. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  8. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  9. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  11. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  12. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
38 more
  1. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  2. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  3. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  4. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  5. 2018Learning Dexterous In-Hand Manipulationcited by 643
  6. 2020Rescaling Egocentric Visioncited by 529
  7. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  8. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  9. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  10. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  11. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  12. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  13. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 263
  14. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 239
  15. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  16. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 215
  17. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  18. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  19. 2023Language-Driven Representation Learning for Roboticscited by 163
  20. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  21. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 160
  22. 2023HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real Worldcited by 159
  23. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  24. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 137
  25. 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 127
  26. 2024LITA: Language Instructed Temporal-Localization Assistantcited by 124
  27. 2022Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videoscited by 110
  28. 2018Actor and Observer: Joint Modeling of First and Third-Person Videoscited by 102
  29. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 95
  30. 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
  31. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 85
  32. 2024Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learningcited by 69
  33. 2024OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulationcited by 67
  34. 2024MyVLM: Personalizing VLMs for User-Specific Queriescited by 58
  35. 2022Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Handscited by 49
  36. 2023AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wildcited by 46
  37. 2024Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Trackingcited by 46
  38. 2024Learning Manipulation by Predicting Interactioncited by 36

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 25; 2026: 91.

116 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  2. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  3. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 117
  4. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  5. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  6. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  7. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  8. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  9. 2026EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldcited by 49
  10. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  11. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  12. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 43
38 more
  1. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  2. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  3. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 29
  4. 2025World Models for Learning Dexterous Hand-Object Interactions from Human Videoscited by 26
  5. 2025MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Trainingcited by 24
  6. 2025In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Datacited by 21
  7. 2026Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stackcited by 20
  8. 2026FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignmentcited by 19
  9. 2025ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrationscited by 17
  10. 2026LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfercited by 17
  11. 2026EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Datacited by 17
  12. 2025GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulationcited by 16
  13. 2025MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agentcited by 15
  14. 2026NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoningcited by 15
  15. 2026HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videoscited by 14
  16. 2025Scaling Cross-Embodiment World Models for Dexterous Manipulationcited by 13
  17. 2025X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scalecited by 12
  18. 2025OPENTOUCH: Bringing Full-Hand Touch to Real-World Interactioncited by 11
  19. 2026ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulationcited by 11
  20. 2026Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrationscited by 11
  21. 2025Developing Vision-Language-Action Model from Egocentric Videoscited by 10
  22. 2026Egocentric World Model for Photorealistic Hand-Object Interaction Synthesiscited by 10
  23. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  24. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 10
  25. 2025Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Explorationcited by 9
  26. 2025METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Modelcited by 9
  27. 2026UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modelingcited by 9
  28. 2026Dexora: Open-source VLA for High-DoF Bimanual Dexteritycited by 9
  29. 2026Do as I Do: Dexterous Manipulation Data from Everyday Human Videoscited by 9
  30. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robotscited by 8
  31. 2026CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelingcited by 8
  32. 2026Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wildcited by 8
  33. 2026MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulationcited by 8
  34. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 8
  35. 2025Survey of Vision-Language-Action Models for Embodied Manipulationcited by 7
  36. 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videoscited by 7
  37. 2026WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videoscited by 7
  38. 2026μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Modelscited by 7

50 most cited of 116 All 116 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
  2. 2026IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining ↗
  3. 2026Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
  4. 2025RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
  5. 2026Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments
  6. 2026VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances
  7. 2026CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
  8. 2025AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning