World Models with Configurable Perception
Real-world observations are noisy and often contain excessive task-irrelevant information. Effective world modeling and planning need to abstract observations into world state representations while filtering out irrelevant information. However, encoders in existing world models are typically non-adaptive, leading to state representations that are easily distracted by task-irrelevant information. As a result, the model may not selectively filter observations to cater to different task demands. To address this problem, we introduce ConfigWM, which realizes configurable perception through task-conditioned state extraction. Given a language description of the task at hand, ConfigWM uses it as...
| Authors | Yijun Shen, Delong Chen, Xianming Hu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 20 October 2026 |
| Last updated at source | 20 October 2026 |
Models and datasets referencing this paper
- YijunShen/ConfigWMDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.