# ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation

arXiv: https://arxiv.org/abs/2509.10952 · HTML: https://mlsanity.com/paper/2509.10952/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2025.

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

- [EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World](https://mlsanity.com/paper/2604.07607/) (2026)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data](https://mlsanity.com/paper/2607.08436/) (2026)
- [ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations](https://mlsanity.com/paper/2510.01607/) (2025)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale](https://mlsanity.com/paper/2512.04537/) (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)
- [ActiveMimic: Egocentric Video Pretraining with Active Perception](https://mlsanity.com/paper/2606.06194/) (2026)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer](https://mlsanity.com/paper/2510.00491/) (2025)
- [Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy](https://mlsanity.com/paper/2603.01953/) (2026)
- [MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training](https://mlsanity.com/paper/2512.15411/) (2025)
- [EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos](https://mlsanity.com/paper/2602.11464/) (2026)
- [Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models](https://mlsanity.com/paper/2606.21672/) (2026)
- [OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies](https://mlsanity.com/paper/2607.03723/) (2026)
- [The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction](https://mlsanity.com/paper/2608.22301/) (2026)
- [Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation](https://mlsanity.com/paper/2601.19406/) (2026)
- [SurgVIL: Scaling Surgical Robot Imitation Learning with Open-source Surgical Videos](https://mlsanity.com/paper/2608.16058/) (2026)
- [Continuous Manifold-Decomposed Impedance Retargeting for Contact-Rich Imitation Learning](https://mlsanity.com/paper/2609.15716/) (2026)
- [EgoSpeedUp: Transferring Human Manipulation Tempo to Robot Policies](https://mlsanity.com/paper/2609.29310/) (2026)

## Abstract (arXiv)

Learning robot manipulation from abundant human videos offers a scalable alternative to costly robot-specific data collection. However, domain gaps across visual, morphological, and physical aspects hinder direct imitation. To effectively bridge the domain gap, we propose ImMimic, an embodiment-agnostic co-training framework that leverages both human videos and a small amount of teleoperated robot demonstrations. ImMimic uses Dynamic Time Warping (DTW) with either action- or visual-based mapping to map retargeted human hand poses to robot joints, followed by MixUp interpolation between paired human and robot trajectories. Our key insights are (1) retargeted human hand trajectories provide informative action labels, and (2) interpolation over the mapped data creates intermediate domains that facilitate smooth domain adaptation during co-training. Evaluations on four real-world manipulation tasks (Pick and Place, Push, Hammer, Flip) across four robotic embodiments (Robotiq, Fin Ray, Allegro, Ability) show that ImMimic improves task success rates and execution smoothness, highlighting its efficacy to bridge the domain gap for robust robot manipulation. The project website can be found at https://sites.google.com/view/immimic.