Article

ALPS: Visual State Encoders for World Models

The study proposes ALPS, a pretrained visual state encoder that unifies three capabilities—physical state information, language alignment, and pixel reconstruction—within a single set of patch tokens. It pretrains a ViT-B/16 from scratch using only still images and text, and further refines it through cross-view self-distillation.

Part of the event: ALPS: A Visual Encoder Unifying Physical State and Language

This page provides a summary and source link only.