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
Blog
Desenvolvedores de IA de fronteira pedem coordenação internacional para conter o ritmo da pesquisa automatizada antes que as capacidades superem o controle
Blog
A marca d'água SynthID do Google é difícil de burlar, mas não resolve a desinformação gerada por IA
Blog
Relatório da OpenAI associa agentes de programação a construções mais rápidas de softwares científicos
Blog