AI & ML
$Z$-sight: Unifying Vision-Language-Action and Latent World Modeling
arXiv cs.RO0 views
arXiv:2611.24940v1 Announce Type: new Abstract: We introduce $Z$-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. $Z$-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, $Z$-sight jointly denoises future spatial tokens and actions at inference without pixel reconstruction or external encoders. Trained on human video and robot trajectories, $Z$-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.
Source:https://arxiv.org/abs/2611.24940PreviousPhoenix: Learning Scene Structure Representations for Generalizable World-Action ModelsNextNeural Circuit Architectural Priors for Rat Locomotion
Related posts

Roblox money is pushing a controversial anorexia treatment
0The Verge

Canva adds an AI ‘off’ button
0The Verge
I Need Your Help Choosing a Final Year Project
0dev.to
GitHub Copilot Review 2026: Is It Still Worth Paying For?
0dev.to
AI Notetakers Now Record Your Client Meetings in Person. Who Asked for Consent?
0dev.to

How to Interpret Logistic Regression and Odds Ratios
0dev.to