cs.RONov 18, 2026

LaST1.0: A Unified Latent World-Action Model with Control-Centric SpatioTemporal Reasoning

Authors: Hao Chen, Xuheng Zhang, Zhuangzhe Wu, Jiaming Liu, Shaobo Zhang, Jialin Gao, Zhonghao Yan, Di Wu, 

Organizations: The Chinese University of Hong Kong · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Simplexity Robotics

Abstract

World-Action Models couple action learning with future prediction, enabling robotic policies to capture environmental dynamics for robust control. However, prevailing methods take a reconstruction-oriented approach to model future videos, allocating substantial capacity to appearance details that are incidental to control. In this work, we reformulate world modeling for manipulation as control-centric future prediction in latent space, and present LaST1.0, a unified latent World-Action Model. Rather than modeling an observation-complete video future, LaST1.0 predicts compact, geometry-aware latent targets derived from future wrist views, focusing the supervision on the evolving robot-object interactions required for fine-grained manipulation. To better support this control-centric paradigm, LaST1.0 revisits the visual input interface and attention mechanism of its unified architecture. It adopts a vision-encoder-free design with a lightweight patch embedder, exposing fine-grained visual cues directly to the backbone, and introduces LaST-Attention for structured spatiotemporal interactions across modalities. Evaluations across two robot embodiments, five challenging manipulation tasks, and three simulation benchmarks---RLBench, LIBERO, and LIBERO-Plus---demonstrate that LaST1.0 achieves state-of-the-art success rates and generalizes to novel scenarios. These results demonstrate the effectiveness of control-centric latent world modeling for robust manipulation.

Figures & tables

Explore similar work

CardsList
  1. LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning

    Nov 10, 2026Xuheng Zhang, Yiming Zhang, Jialin Gao +14World Models for RoboticsWorld Action Models

  2. LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation

    Aug 4, 2026Fan Yang, Yuting Su, Xiaobo Wang +7World Models for RoboticsLatent Visual Reasoning