# X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale

arXiv: https://arxiv.org/abs/2512.04537 · HTML: https://mlsanity.com/paper/2512.04537/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [VideoDex: Learning Dexterity from Internet Videos](https://mlsanity.com/paper/2212.04498/) (2022)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [Universal Actions for Enhanced Embodied Foundation Models](https://mlsanity.com/paper/2501.10105/) (2025)
- [Phantom: Training Robots Without Robots Using Only Human Videos](https://mlsanity.com/paper/2503.00779/) (2025)
- [Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos](https://mlsanity.com/paper/2510.21571/) (2025)
- [TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System](https://mlsanity.com/paper/2511.02832/) (2025)
- [EgoZero: Robot Learning from Smart Glasses](https://mlsanity.com/paper/2505.20290/) (2025)
- [Human2Robot: Learning Robot Actions from Paired Human-Robot Videos](https://mlsanity.com/paper/2502.16587/) (2025)
- [MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training](https://mlsanity.com/paper/2509.22199/) (2025)
- [H2R: A Human-to-Robot Data Augmentation for Robot Pre-training from Videos](https://mlsanity.com/paper/2505.11920/) (2025)
- [ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation](https://mlsanity.com/paper/2509.10952/) (2025)

## Built on by (most cited first, 12 of 12)

- [Mitty: Diffusion-based Human-to-Robot Video Generation](https://mlsanity.com/paper/2512.17253/) (2025)
- [OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning](https://mlsanity.com/paper/2512.13100/) (2025)
- [Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines](https://mlsanity.com/paper/2604.23001/) (2026)
- [StreamingEffect: Real-Time Human-Centric Video Effect Generation](https://mlsanity.com/paper/2605.17019/) (2026)
- [Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration](https://mlsanity.com/paper/2605.17423/) (2026)
- [OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation](https://mlsanity.com/paper/2605.12038/) (2026)
- [RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation](https://mlsanity.com/paper/2607.06558/) (2026)
- [ActionMap: Robot Policy Learning via Voxel Action Heatmap](https://mlsanity.com/paper/2606.06904/) (2026)
- [SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution](https://mlsanity.com/paper/2605.19319/) (2026)
- [NavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation](https://mlsanity.com/paper/2609.30770/) (2026)
- [PAI-Actor: Cinematic Multi-Character Replacement in Dynamic Scenes](https://mlsanity.com/paper/2609.05918/) (2026)
- [HuRo: Robotizing Human Videos for Scalable VLA Pretraining](https://mlsanity.com/paper/2609.10706/) (2026)

## Abstract (arXiv)

The advancement of embodied AI has unlocked significant potential for intelligent humanoid robots. However, progress in both Vision-Language-Action (VLA) models and world models is severely hampered by the scarcity of large-scale, diverse training data. A promising solution is to "robotize" web-scale human videos, which has been proven effective for policy training. However, these solutions mainly "overlay" robot arms to egocentric videos, which cannot handle complex full-body motions and scene occlusions in third-person videos, making them unsuitable for robotizing humans. To bridge this gap, we introduce X-Humanoid, a generative video editing approach that adapts the powerful Wan 2.2 model into a video-to-video structure and finetunes it for the human-to-humanoid translation task. This finetuning requires paired human-humanoid videos, so we designed a scalable data creation pipeline, turning community assets into 17+ hours of paired synthetic videos using Unreal Engine. We then apply our trained model to 60 hours of the Ego-Exo4D videos, generating and releasing a new large-scale dataset of over 3.6 million "robotized" humanoid video frames. Quantitative analysis and user studies confirm our method's superiority over existing baselines: 69% of users rated it best for motion consistency, and 62.1% for embodiment correctness.