跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24940 · v1

$Z$-sight: Unifying Vision-Language-Action and Latent World Modeling

首次提交 2026-11-19 02:59
版本更新 2026-11-19 02:59
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

We introduce ZZ-sight, a unified robot foundation model that couples vision-language-action (VLA) and generative latent world modeling. Video-based world action models (WAMs) show the value of joint future-and-action generation for control, yet inherit the heavy cost of video generators. Recent latent-space policies avoid pixel generation, yet typically align intermediate features or rely on frozen target encoders, decoupling future prediction from the VLM's native feature space. ZZ-sight instead predicts the future directly in the visual token space in which its VLM perceives the present. Coupling a foresight expert and a continuous action expert with the VLM in a mixture-of-transformers, ZZ-sight jointly denoises future spatial tokens and actions at inference without pixel reconstruction or external encoders. Trained on human video and robot trajectories, ZZ-sight achieves 81.9% success on SIMPLE (+9.6 points over the strongest baseline) and 73.3% across six Unitree G1 tasks (+20.0 points) at 110 ms per chunk, while remaining competitive on tabletop benchmarks.

作者备注:Project page: https://junjieye.com/Z-sight/

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 02:59 · 最新观测版本

$Z$-sight: Unifying Vision-Language-Action and Latent World Modeling

We introduce ZZ-sight, a unified robot foundation model that couples vision-language-action (VLA) and generative latent world modeling. Video-based world action models (WAMs) show the value of joint future-and-action generation for control, yet inherit the heavy cost of video generators. Recent latent-space policies avoid pixel generation, yet typically align intermediate features or rely on frozen target encoders, decoupling future prediction from the VLM's native feature space. ZZ-sight instead predicts the future directly in the visual token space in which its VLM perceives the present. Coupling a foresight expert and a continuous action expert with the VLM in a mixture-of-transformers, ZZ-sight jointly denoises future spatial tokens and actions at inference without pixel reconstruction or external encoders. Trained on human video and robot trajectories, ZZ-sight achieves 81.9% success on SIMPLE (+9.6 points over the strongest baseline) and 73.3% across six Unitree G1 tasks (+20.0 points) at 110 ms per chunk, while remaining competitive on tabletop benchmarks.

查看此版本解读 →查看此版本原文 ↗