notesum.ai

Published at November 15

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

cs.CL
cs.CV

Released Date: November 15, 2024

Authors: Weiyun Wang1, Zhe Chen2, Wenhai Wang3, Yue Cao2, Yangzhou Liu2, Zhangwei Gao4, Jinguo Zhu4, Xizhou Zhu5, Lewei Lu6, Yu Qiao4, Jifeng Dai5

Aff.: 1Fudan University; 2Nanjing University; 3The Chinese University of Hong Kong; 4OpenGVLab, Shanghai AI Laboratory; 5Tsinghua University; 6SenseTime Research

Arxiv: http://arxiv.org/abs/2411.10442v1