mlsanityData to 7 Oct 2026

Phantom: Training Robots Without Robots Using Only Human Videos

arXiv 2503.00779 ↗First posted 2 Mar 2025cs.ROcited by 64

Not on the map. Why?

Abstract (arXiv)

Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale. We present a scalable framework for training manipulation policies directly from human video demonstrations, requiring no robot data. Our method converts human demonstrations into robot-compatible observation-action pairs using hand pose estimation and visual data editing. We inpaint the human arm and overlay a rendered robot to align the visual domains. This enables zero-shot deployment on real hardware without any fine-tuning. We demonstrate strong success rates-up to 92%-on a range of tasks including deformable object manipulation, multi-object sweeping, and insertion. Our approach generalizes to novel environments and supports closed-loop execution. By demonstrating that effective policies can be trained using only human videos, our method broadens the path to scalable robot learning.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 30; 2026: 34.

64 papers.

Sort:

By area:

  1. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  2. 2026EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the Worldcited by 49
  3. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 47
  4. 2025CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrationscited by 39
  5. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  6. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  7. 2025EgoZero: Robot Learning from Smart Glassescited by 28
  8. 2025EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Datacited by 27
  9. 2025X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Realcited by 25
  10. 2025MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Trainingcited by 24
  11. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 20
  12. 2025Robot Learning from a Physical World Modelcited by 18
38 more
  1. 2025AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletonscited by 17
  2. 2026LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfercited by 17
  3. 2025DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policycited by 16
  4. 2025Dexterous World Modelscited by 15
  5. 2026RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulationcited by 15
  6. 2026HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videoscited by 14
  7. 2025Object-centric 3D Motion Field for Robot Learning from Human Videoscited by 13
  8. 2025Mitty: Diffusion-based Human-to-Robot Video Generationcited by 13
  9. 2025X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scalecited by 12
  10. 2026ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulationcited by 11
  11. 2025Developing Vision-Language-Action Model from Egocentric Videoscited by 10
  12. 2025Mask2IV: Interaction-Centric Video Generation via Mask Trajectoriescited by 10
  13. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  14. 2025H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videoscited by 8
  15. 2026ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretrainingcited by 8
  16. 2025Scaffolding Dexterous Manipulation with Vision-Language Modelscited by 7
  17. 2025Robot Learning from Any Imagescited by 7
  18. 2026Masked Visual Actions for Unified World Modelingcited by 7
  19. 2025X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrationscited by 6
  20. 2025ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flowcited by 5
  21. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  22. 2026Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learningcited by 5
  23. 2025Latent Adaptive Planner for Dynamic Manipulationcited by 4
  24. 2025R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulationcited by 4
  25. 2026OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptationcited by 4
  26. 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editingcited by 4
  27. 2026Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Modelscited by 3
  28. 2026PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generationcited by 3
  29. 2026A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policiescited by 3
  30. 2026Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLAcited by 3
  31. 2025Robust Human Registration with Body Part Segmentation on Noisy Point Cloudscited by 2
  32. 2025EmbodiSwap for Zero-Shot Robot Imitation Learningcited by 2
  33. 2025DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulationcited by 2
  34. 2026EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videoscited by 2
  35. 2026CRAFT: Video Diffusion for Bimanual Robot Data Generationcited by 2
  36. 2026GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulationcited by 2
  37. 2026LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisitioncited by 2
  38. 2025IGen: Scalable Data Generation for Robot Learning from Open-World Imagescited by 1

50 most cited of 64 All 64 (JSON)