arXiv 2025 ยท preprint

Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning

Figure 1 of the survey: quarterly count of visual-reasoning papers

Jing Bi, Susan Liang, Xiaofei Zhou, Pinxin Liu, Junjia Guo, Yunlong Tang, Luchuan Song, Chao Huang, Ali Vosoughi, Guangyu Sun, Jinxi He, Jiarui Wu, Shu Yang, Daoan Zhang, Chen Chen, Lianggong Bruce Wen, Zhang Liu, Jiebo Luo, Chenliang Xu

Surveys multimodal reasoning methods, evaluation challenges, post-training optimization and test-time inference for vision-language systems.

Surveys multimodal reasoning methods, evaluation challenges, post-training optimization and test-time inference for vision-language systems.

All publications