# MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

arXiv: https://arxiv.org/abs/2509.09769 · HTML: https://mlsanity.com/paper/2509.09769/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2025.

## Built on by (most cited first, 20 of 20)

- [Act2Goal: From World Model To General Goal-conditioned Policy](https://mlsanity.com/paper/2512.23541/) (2025)
- [PlayWorld: Learning Robot World Models from Autonomous Play](https://mlsanity.com/paper/2603.09030/) (2026)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [Mitty: Diffusion-based Human-to-Robot Video Generation](https://mlsanity.com/paper/2512.17253/) (2025)
- [WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time](https://mlsanity.com/paper/2607.06988/) (2026)
- [In-Context Robot Learning with VLM Agents](https://mlsanity.com/paper/2609.19138/) (2026)
- [Learning Human-Humanoid Coordination for Collaborative Object Carrying](https://mlsanity.com/paper/2510.14293/) (2025)
- [X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations](https://mlsanity.com/paper/2511.04671/) (2025)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time](https://mlsanity.com/paper/2606.15631/) (2026)
- [Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer](https://mlsanity.com/paper/2510.00491/) (2025)
- [SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM](https://mlsanity.com/paper/2603.08269/) (2026)
- [SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework](https://mlsanity.com/paper/2605.20373/) (2026)
- [In-Context World Modeling for Robotic Control](https://mlsanity.com/paper/2606.26025/) (2026)
- [Bimanual Robot Manipulation via Multi-Agent In-Context Learning](https://mlsanity.com/paper/2604.20348/) (2026)
- [Learning of Robot Safety Policies via Adversarial Synthetic Scenarios](https://mlsanity.com/paper/2606.05952/) (2026)
- [ContextFlow: In-Context Flow Matching for Robot Manipulation](https://mlsanity.com/paper/2609.06852/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance](https://mlsanity.com/paper/2603.12120/) (2026)
- [Learning Transferable World-Action Models from Task-Paired Human Videos](https://mlsanity.com/paper/2610.14351/) (2026)

## Abstract (arXiv)

We aim to enable humanoid robots to efficiently solve new manipulation tasks from a few video examples. In-context learning (ICL) is a promising framework for achieving this goal due to its test-time data efficiency and rapid adaptability. However, current ICL methods rely on labor-intensive teleoperated data for training, which restricts scalability. We propose using human play videos -- continuous, unlabeled videos of people interacting freely with their environment -- as a scalable and diverse training data source. We introduce MimicDroid, which enables humanoids to perform ICL using human play videos as the only training data. MimicDroid extracts trajectory pairs with similar manipulation behaviors and trains the policy to predict the actions of one trajectory conditioned on the other. Through this process, the model acquired ICL capabilities for adapting to novel objects and environments at test time. To bridge the embodiment gap, MimicDroid first retargets human wrist poses estimated from RGB videos to the humanoid, leveraging kinematic similarity. It also applies random patch masking during training to reduce overfitting to human-specific cues and improve robustness to visual differences. To evaluate few-shot learning for humanoids, we introduce an open-source simulation benchmark with increasing levels of generalization difficulty. MimicDroid outperformed state-of-the-art methods and achieved nearly twofold higher success rates in the real world. Additional materials can be found on: ut-austin-rpl.github.io/MimicDroid