# ConfigWM: Configurable-Perception World Models via Task-Conditioned State Extraction

- Source: HuggingFace Daily Papers
- Published: 2026-10-20T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/mkpczlyq71web1feqt1pzydm2
- Original: https://huggingface.co/papers/2610.27914

## Summary

ConfigWM proposes a configurable perception mechanism that uses task language descriptions as configuration signals to guide the mapping of visual embeddings into task-specific state spaces, selectively retaining task-relevant information and suppressing distractions. In environments with progressively increasing distraction, existing methods show a marked decline in planning success rate, while ConfigWM remains relatively stable, averaging 22.3% higher than the strongest competing method. Physical-quantity probing (Pearson r +0.365) and distracted-to-clean retrieval (+75.5%) also show consistent improvements.