VLAC

VLAC is a vision-language-action-critic model for dense progress rewards and action generation in real-world robot reinforcement learning.

Recommended citation: Shaopeng Zhai, Qi Zhang, Tianyi Zhang, Fuxian Huang, Haoran Zhang, Ming Zhou, Shengzhe Zhang, Litao Liu, Sixu Lin, and Jiangmiao Pang. A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning. arXiv, 2025.
Download Paper