Jian Liang

Ph.D. Student, Wuhan University

Google Scholar GitHub Email Wechat

Short Bio

I am a 2nd-year Ph.D. student in the School of Computer Science at Wuhan University, advised by Prof. Mang Ye. Previously, I received my bachelor degree from the School of Mathematics and Statistics at Wuhan University in 2024. If you are interested in collaborating with me or want to have a chat, feel free to contact me through e-mail or Wechat.

My research mainly focuses on Multimodal Large Language Models and Post Training.

Selected Publications

†: co-first author

Harmonious Low-Rank Adaptation for Multimodal Large Language Models

Jian Liang, Wenke Huang, Xianda Guo, Guancheng Wan, Bo Du, Mang Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

Paper Code

LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models

Jian Liang, Wenke Huang, Guancheng Wan, Qu Yang, Mang Ye

Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Oral Presentation (96/13008, 0.7%)

Paper Code

Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models

Yiyang Fang, Jian Liang†, Wenke Huang, He Li, Kehua Su, Mang Ye

International Conference on Machine Learning (ICML), 2025

Spotlight (313/12107, 2.6%)

Paper Code

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

Wenke Huang, Jian Liang†, Guancheng Wan, Didi Zhu, He Li, Jiawei Shao, Mang Ye, Bo Du, Dacheng Tao

International Conference on Machine Learning (ICML), 2025

Paper Code

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Wenke Huang, Jian Liang†, Xianda Guo, Yiyang Fang, Guancheng Wan, Xuankun Rong, Chi Wen, Zekun Shi, Qingyun Li, Didi Zhu, Yanbiao Ma, Ke Liang, Bin Yang, He Li, Jiawei Shao, Mang Ye, Bo Du

arXiv, 2025

Paper Code

Honors and Awards

Academic Service

Education