top of page
Efficient VLM and Evaluation
Law of Vision Representations in MLLMs
Shijia Yang, Bohan Zhai, Quanzeng You, Jianbo Yuan, Hongxiang Yang, Chenfeng Xu [COLM 2025][code][Some thoughts about current developments in MLLM]
CaptionQA: Is Your Caption as Useful as the Image Itself?
Shijia Yang, Yunong Liu, Bohan Zhai, Ximeng Sun, Zicheng Liu, Emad Barsoum, Manling Li, Chenfeng Xu [Submit your caption to see it is really useful?]
bottom of page