MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking
Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We present MimicX, a policy-in-the-loop framework that uses execution feedback to refine video-driven humanoid motion tracking. Starting from reconstructed and retargeted motion, MimicX localizes difficult transitions and affected body regions, then jointly adapts tracking objectives and the reset curriculum for policy continuation. Repeated rollout verification selects execution-priority improvements subject to tracking guards. Across four core video tasks, Mim...
| Authors | Shuaijun Liu, Chenglong Zhang, Xuhao Liu et al. |
|---|---|
| Primary category | cs.RO |
| Published | 6 October 2026 |
| Last updated at source | 6 October 2026 |
Popularity, last 3 days
0 now (-4 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- Shuaijun/MimicX-AssetsDataset · cited by
Recent changes
- 16 Oct 2026 Description: Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We presen → Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We presen
- 16 Oct 2026 Topics added cs.RO, cs.AI removed hf-daily-papers, policy-in-the-loop, execution feedback, motion tracking, reset curriculum, rollout verification, tracking guards, heterogeneous execution
Changes detected by Silytics between refreshes of the source.
Models and datasets referencing this paper
- Shuaijun/MimicX-AssetsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.