RESEARCH PAPER

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training

Haoyun Li; Ivan Zhang; Runqi Ouyang; Xiaofeng Wang; Zheng Zhu; Zhiqin Yang; Zhentao Zhang; Boyuan Wang; Chaojun Ni; Wenkang Qin; Xinze Chen; Yun Ye; Guan Huang; Zhenbo Song; Xingang Wang

Classification

View four quadrants
Major category
Datasets
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Not assigned

Category review. The primary pipeline converts human demonstrations into robot-looking training videos paired with retargeted actions, then trains a separate VLA; it supplies aligned synthetic supervision rather than an inference-time WAM. The cataloged contribution is a dataset/data-generation method or evaluation/simulation resource, not the architecture of an evaluated or external policy. Reading evidence

AT A GLANCE

Contribution

MimicDreamer converts human demonstrations into robot-looking videos paired with retargeted actions, then post-trains a separate π0 policy. The contribution is training-data alignment across viewpoint, embodiment and appearance. Physical-task results improve with added synthetic demonstrations, but real-robot supervision remains part of the evaluated pipeline and several headline summaries conflict with the tables.

Abstract

An abstract has not been added yet.

Affiliations

GigaAI; CASIA; NJUST; Tsinghua University