Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer

תקציר מקורי באנגליתarXiv:2610.11416v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vision-Language Models (VLMs). However, such VLM backbones offer insufficient physical dynamics priors, which limits the generalization capabilities of robot policies. Recent efforts therefore integrate video-generation World Models (WMs) into robot policies through various strategies, using predictive dynamics to facilitate action generation. Despite these advances, harnessing semantic understanding and dynamics prediction as complementary guidance for action generation remains challenging. In this paper, we introduce $\mathrm{ACT}^3$, a simple yet effective Action-Centric T