cs.RONov 18, 2026

ZZ-sight: Unifying Vision-Language-Action and Latent World Modeling

Authors: Junjie Ye, Yiqi Zhao, Muchen Xu, Celina Shiyu Wang, Hao Dong, Ruohai Ge, Rong Xue, Benjamin J Kolligs, 

Organizations: Maven Robotics · University of Southern California

Abstract

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.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Vision-Language-Action or World-Action? Just Action Models

    Oct 27, 2026Yonghao Yu, Lang Huang, Runyi Li +1VLA Model TrainingWorld Action Models

  2. WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction

    Oct 13, 2026Haomin Wang, Anqiong Ji, Ke Wang +4World Models for RoboticsWorld Action Models