# Phantom: Training Robots Without Robots Using Only Human Videos

arXiv: https://arxiv.org/abs/2503.00779 · HTML: https://mlsanity.com/paper/2503.00779/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2025.

## Built on by (most cited first, 30 of 70)

- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World](https://mlsanity.com/paper/2604.07607/) (2026)
- [Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models](https://mlsanity.com/paper/2606.17846/) (2026)
- [Emergence of Human to Robot Transfer in Vision-Language-Action Models](https://mlsanity.com/paper/2512.22414/) (2025)
- [CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations](https://mlsanity.com/paper/2505.04999/) (2025)
- [Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations](https://mlsanity.com/paper/2507.00990/) (2025)
- [EgoZero: Robot Learning from Smart Glasses](https://mlsanity.com/paper/2505.20290/) (2025)
- [EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data](https://mlsanity.com/paper/2509.19626/) (2025)
- [X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real](https://mlsanity.com/paper/2505.07096/) (2025)
- [MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training](https://mlsanity.com/paper/2509.22199/) (2025)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [Robot Learning from a Physical World Model](https://mlsanity.com/paper/2511.07416/) (2025)
- [DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy](https://mlsanity.com/paper/2506.20668/) (2025)
- [RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation](https://mlsanity.com/paper/2604.19092/) (2026)
- [AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons](https://mlsanity.com/paper/2503.03081/) (2025)
- [Dexterous World Models](https://mlsanity.com/paper/2512.17907/) (2025)
- [LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer](https://mlsanity.com/paper/2602.10556/) (2026)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [Object-centric 3D Motion Field for Robot Learning from Human Videos](https://mlsanity.com/paper/2506.04227/) (2025)
- [Mitty: Diffusion-based Human-to-Robot Video Generation](https://mlsanity.com/paper/2512.17253/) (2025)
- [ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation](https://mlsanity.com/paper/2602.00557/) (2026)
- [X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale](https://mlsanity.com/paper/2512.04537/) (2025)
- [Developing Vision-Language-Action Model from Egocentric Videos](https://mlsanity.com/paper/2509.21986/) (2025)
- [Mask2IV: Interaction-Centric Video Generation via Mask Trajectories](https://mlsanity.com/paper/2510.03135/) (2025)
- [OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning](https://mlsanity.com/paper/2512.13100/) (2025)
- [ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining](https://mlsanity.com/paper/2606.17200/) (2026)
- [Scaffolding Dexterous Manipulation with Vision-Language Models](https://mlsanity.com/paper/2506.19212/) (2025)
- [H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos](https://mlsanity.com/paper/2512.09406/) (2025)
- [Masked Visual Actions for Unified World Modeling](https://mlsanity.com/paper/2607.19343/) (2026)
- [Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning](https://mlsanity.com/paper/2607.14183/) (2026)

## 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.