ALPS: A Unified Visual State Encoder for World Models from UCSC and Google
UCSC-VLAA · hf · 2026-10-22
ALPS is a pretrained visual encoder for world models that unifies physical-state prediction, language alignment, and pixel reconstruction. It combines the strengths of spatial/self-supervised encoders (state probing) and image-text encoders (language alignment), achieving competitive results across all three interfaces. Code and weights are open-sourced.
More from Research
- Michael Levin polls the public: how do physical, living, and minds overlap? — drmichaellevin · 2026-10-22
- ICLR reviewer: 2 of 3 assigned papers are complete AI slop, worst batch ever seen — AkariAsai · 2026-10-22
- Training-free 20B model Viveki generates real-time video heatmaps under 150ms — not-ekalabya · 2026-10-22
- JD paper proposes ROAD MOPD: cross-teacher guarding to fix gradient conflicts in multi-teacher distillation — teortaxesTex · 2026-10-22
- A complete math roadmap for machine learning: linear algebra, calculus, probability — TivadarDanka · 2026-10-22
- Microsoft's ScholarEvolve lets agents improve by reading papers, lifting Qwen's AppWorld score from 69% to 81.4% — bendee983 · 2026-10-22