一作CVPR 2026Poster· Computer Vision & Pattern Recognition
ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
Linqing Zhong · Yi Liu · Yifei Wei · Ziyu Xiong · Si Liu · Guanghui Ren
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Linqing Zhong · Yi Liu · Yifei Wei · Ziyu Xiong · Si Liu · Guanghui Ren
Yifei Wei · Linqing Zhong · Yi Liu · Yuxiang Lu · Xindong He · Maoqing Yao · Guanghui Ren
Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into executable physical actions. However, prevailing approaches typically adopt a monolithic generation paradigm, directly mapping visual-linguistic feat...
Heqing Yang · Yang Yi · Linqing Zhong · Linjiang Huang · Si Liu