ALPS: Visual State Encoders for World Models

The paper introduces ALPS, a pretrained visual state encoder that integrates physical-state information, native language alignment, and pixel reconstruction into a single representation. Trained from scratch on still images and text, ALPS uses language, reconstruction, and spatial correspondence objectives, followed by cross-view self‑distillation. In evaluations across fifteen encoders, ALPS achieves the lowest aggregate LIBERO state‑probe error among ViT‑B models, while also delivering strong language alignment, accurate pixel reconstruction, and high policy success in downstream world‑model tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• efficiency
• safety