FACT: Failure-Aware Causal Training for World-Action Models
Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the future-prediction ability of video models, many WAMs generate future videos and recover actions with inverse-dynamics models, or use these predicted videos as goal conditions for action generation. In both cases, the world model is trained mostly on successful demonstrations and has little reason to predict the consequences of bad actions. We introduce FACT, a causal World-Action Model that predicts future video and task progress conditioned on the executed action. This action-conditioned interface allows failure rollouts to supervise a...
| Authors | Quanquan Peng, Yutong Liang, Rui Yan et al. |
|---|---|
| Primary category | cs.RO |
| Published | 10 August 2026 |
| Last updated at source | 13 October 2026 |
Models and datasets referencing this paper
- Bariona/robotwin-v2Dataset
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 Information may be incomplete or out of date.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.