arXiv 2610.30120 · cs.CV · 2026-10-21
ALPS: Visual State Encoders for World Models
Yanqing Liu, Letian Zhang, Chengzhi Liu, Zijun Wang, Jieru Mei, Hongliang Fei, Yuyin Zhou, Cihang Xie
UCSC-VLAA
在最新榜 #293 本站收录于 2026-10-24
一句话要点
UCSC-VLAA 的 ALPS 是给世界模型用的视觉状态编码器：在同一组 patch token 里同时具备物理状态信息、原生语言对齐和像素重建能力；只用静态图像和文本，从零预训练 ViT-B/16，目标同时含语言、重建和空间对应。
UCSC-VLAA's ALPS is a visual state encoder for world models that unifies physical-state information, native language alignment and pixel reconstruction in one set of patch tokens, pretraining a ViT-B/16 from scratch on still images and text with language, reconstruction and spatial-correspondence objectives.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉理解与 3D
- Spectral-Spatial Interpretation ▲753
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲189
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲172
- DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations ▲161
同主题：机器人与具身
- Has GPT-6-Astra Achieved Embodied Intelligence? 2026-10-15 · ▲421
- In-Context Learning for Robots: Methods and Applications 2026-09-28 · ▲388
- GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives 2026-09-30 · ▲310
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents 2026-10-16 · ▲294
- Reflex: Visually Grounded Reactive Humanoid Control 2026-10-08 · ▲154
同机构：UCSC-VLAA
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。