Learning Visual Feature-Based World Models via Residual Latent Action
World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video pixels, offering a promising alternative that is more efficient and less prone to hallucination. However, current feature-based approaches rely on direct regression, which leads to blurry or collapsed predictions in complex interactions, while generative modeling in high-dimensional feature spaces still remains challenging. In this work, we discover that a new type of latent action representation, which we refer to as Residual Latent Action (RLA), can be ...
| Authors | Xinyu Zhang, Zhengtong Xu, Yutian Tao et al. |
|---|---|
| Primary category | cs.CV |
| Published | 8 May 2026 |
| Last updated at source | 5 October 2026 |
Connected in the knowledge graph
- xyzhang368/RLA-WMDataset · cited by
Models and datasets referencing this paper
- xyzhang368/RLA-WMDataset
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 Information may be incomplete or out of date.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.