作者位次 #6/10ACL 2026Poster· Natural Language Processing
On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
Changyu Liu · Yiyang Liu · Taowen Wang · Qiao Zhuang · James Chenhao Liang · Wenhao Yang · Renjing Xu · Qifan Wang · Dongfang Liu · Cheng Han
摘要
Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular, they are primarily trained via supervised fine-tuning or tra...