作者位次 #3/6ACL 2026Findings· Findings of ACL
MGPO : Thinking with Images via Multi-Turn Grounding-Based Reinforcement Learning
Xinyu Huang · Yuhao Dong · Weiwei Tian · Bo Li · Rui Feng · Ziwei Liu
摘要
State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. In this paper, we propose Multi-turn Grounding-based Policy Optimization (MGPO),...