# X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations

arXiv: https://arxiv.org/abs/2511.04671 · HTML: https://mlsanity.com/paper/2511.04671/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 59 of its 68 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 59)

- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [LESS: Selecting Influential Data for Targeted Instruction Tuning](https://mlsanity.com/paper/2402.04333/) (2024)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [Human-to-Robot Imitation in the Wild](https://mlsanity.com/paper/2207.09450/) (2022)
- [Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning](https://mlsanity.com/paper/2402.00530/) (2024)
- [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024)
- [Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos](https://mlsanity.com/paper/2103.16817/) (2021)
- [Ambient Diffusion: Learning Clean Distributions from Corrupted Data](https://mlsanity.com/paper/2305.19256/) (2023)
- [XIRL: Cross-embodiment Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.03911/) (2021)
- [VideoDex: Learning Dexterity from Internet Videos](https://mlsanity.com/paper/2212.04498/) (2022)
- [Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube](https://mlsanity.com/paper/2202.10448/) (2022)
- [Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation](https://mlsanity.com/paper/2203.13251/) (2022)
- [XSkill: Cross Embodiment Skill Discovery](https://mlsanity.com/paper/2307.09955/) (2023)
- [Phantom: Training Robots Without Robots Using Only Human Videos](https://mlsanity.com/paper/2503.00779/) (2025)
- [OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation](https://mlsanity.com/paper/2410.11792/) (2024)
- [Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning](https://mlsanity.com/paper/2501.06994/) (2025)
- [Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent](https://mlsanity.com/paper/2302.09057/) (2023)
- [Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers](https://mlsanity.com/paper/2403.12943/) (2024)

## Built on by (most cited first, 6 of 6)

- [Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics](https://mlsanity.com/paper/2606.12365/) (2026)
- [DADP: Domain Adaptive Diffusion Policy](https://mlsanity.com/paper/2602.04037/) (2026)
- [LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment](https://mlsanity.com/paper/2604.10677/) (2026)
- [SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation](https://mlsanity.com/paper/2609.21983/) (2026)
- [Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation](https://mlsanity.com/paper/2609.26672/) (2026)
- [X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets](https://mlsanity.com/paper/2609.35715/) (2026)

## Abstract (arXiv)

Human videos are a scalable source of training data for robot learning. However, humans and robots significantly differ in embodiment, making many human actions infeasible for direct execution on a robot. Still, these demonstrations convey rich object-interaction cues and task intent. Our goal is to learn from this coarse guidance without transferring embodiment-specific, infeasible execution strategies. Recent advances in generative modeling tackle a related problem of learning from low-quality data. In particular, Ambient Diffusion is a recent method for diffusion modeling that incorporates low-quality data only at high-noise timesteps of the forward diffusion process. Our key insight is to view human actions as noisy counterparts of robot actions. As noise increases along the forward diffusion process, embodiment-specific differences fade away while task-relevant guidance is preserved. Based on these observations, we present X-Diffusion, a cross-embodiment learning framework based on Ambient Diffusion that selectively trains diffusion policies on noised human actions. This enables effective use of easy-to-collect human videos without sacrificing robot feasibility. Across five real-world manipulation tasks, we show that X-Diffusion improves average success rates by 16% over naive co-training and manual data filtering. The project website is available at https://portal-cornell.github.io/X-Diffusion/.