MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation.
Jinsheng HuangLiang ChenTaian GuoFu ZengYusheng ZhaoBohan WuYe YuanHaozhe ZhaoZhihui GuoYichi ZhangJingyang YuanWei JuLuchen LiuTianyu LiuBaobao ChangMing ZhangPublished in: CoRR (2024)