ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

Zhongyi Zhou; Yichen Zhu; Minjie Zhu; Junjie Wen; Ning Liu; Zhiyuan Xu; Weibin Meng; Yaxin Peng; Chaomin Shen; Feifei Feng; Yi Xu

doi:10.18653/v1/2025.emnlp-main.273

EMNLP2025顶会

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Yaxin Peng, Chaomin Shen, Feifei Feng, Yi Xu

DOI 出版方

2025年份

6被引次数

12顶会引用

摘要

Visual Grounding Q: Provide the bounding box coordinate of the police vehicle. A: [0.26, 0.56, 0.44, 0.71] Image Captioning Q: Provide a one-sentence caption for the image. A: A vintage-style street clock stands prominently at a city intersection, with a historic brick building in the background and several cars, including a police car, navigating the crosswalk.