SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models
arXiv:2607.25912v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong potential for general robot manipulation, but most existing models rely on 2D visual-language backbones and lack fine-grained 3D understanding of target objects, especially under occlusion, pose variation, scale changes, and precise spatial interaction. We propose an object-centric 3D representation alignment framework built upon $\pi_0$, using SAM3D as a frozen 3D teacher to provide target-obje...
arXiv cs.RO
·Zonghe Liu (University of Hong Kong), Shanyuan Jie (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Xiaoquan Sun (Huazhong University of Science and Technology), Chen Cao (University of Hong Kong), Zetian Xu (University of Hong Kong), Zongsheng Liu (Beijing University of Aeronautics and Astronautics), Jiayu Chen (University of Hong Kong, Infiforce)
·
// relacionados
Leia também
Editorial
RynnValue: o relógio do vídeo como recompensa para robôs
Blog
Anthropic aplica marca d'água a todas as saídas do Claude globalmente, com marcas que "podem persistir mesmo após alguma edição"
Blog
webAI lança TwIL-LM: uma família de modelos de lógica formal de 1,7B e 3B para autoformalização em hardware local
Blog