SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models
Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging. Simulation offers structured motion supervision, but appearance differences hinder direct transfer, and inaccurate simulation predictions can misguide real-video generation. We present SimForcing, a simulation-guided framework that uses simulation both as a source of transferable motion knowledge and as a controllable reference for prediction. First, we transfer motion knowledge from a simulation teacher through latent-motion distillation, aligning temporal changes in latent space to internaliz...
| Authors | Xiaodong Wang, Tianle Li, Chuanxin Song et al. |
|---|---|
| Primary category | cs.RO |
| Published | 5 October 2026 |
| Last updated at source | 5 October 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Description: Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging. Simulation offers structured motion superv → Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging. Simulation offers structured motion superv
- 16 Oct 2026 Topics added cs.RO, cs.AI, cs.CV removed hf-daily-papers, action-conditioned robot world models, latent-motion distillation, multi-block simulation conditioning, condition dropout, classifier-free guidance, vision-language-action model
Changes detected by Silytics between refreshes of the source.
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 Information may be incomplete or out of date.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.