作者位次 #2/10ICLR 2026Poster
DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
Haowen Gao · zhenyu zhang · Liang Pang · Fangda Guo · hongjian dou · Guannan Lv · ShaoGuo Liu · Tingting Gao · Huawei Shen · Xueqi Cheng