Title
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning Yi-Fan Zhang Xingyu Lu X. Hu Chaoyou Fu Bin Wen ... Jianfei Chen Fan Yang Z. Zhang Tingting Gao Liang Wang OffRL LRM 46 0 0 05 May 2025
MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models Wulin Xie Yuyao Zhang Chaoyou Fu Yang Shi Bingyan Nie Hongkai Chen Z. Zhang Liang Wang Tieniu Tan 36 1 0 04 Apr 2025