GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning
GeneralVLA-2 addresses limitations in vision-language-action systems by introducing GeoFuse-MV3D for improved 3D reconstruction and an enhanced KnowledgeBank for better memory mana…
Hugging Face · Daily Papers
·Haoyu Wang, Guoqing Ma
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Haoyu Wang, Guoqing Ma, Zeyu Zhang, Yandong Guo, Boxin Shi, Hao Tang
- 3 upvotes da comunidade
- Temas: GeoFuse-MV3D, MV-SAM3D, KnowledgeBank, vision-language-action systems, 3D reconstruction, geometric prior
Resumo
Resumo original (em inglês), extraído do paper:
GeneralVLA-2 addresses limitations in vision-language-action systems by introducing GeoFuse-MV3D for improved 3D reconstruction and an enhanced KnowledgeBank for better memory management in robotic manipulation tasks.
// relacionados
