Biography
I am a 2nd year Ph.D. student at MMLab of The Chinese University of Hong Kong, supervised by Prof. Dahua Lin. Prior to this, I received my B.E. degree in Computer Science and Technology at Xi'an Jiaotong University in 2024.My current research focuses on:
◆ Large Vision-Language Models (LVLMs): Visual-Question-Answering, Video-Understanding, Modality-Alignment, Multimodal-Retrieval, Chart-Parsing, Visual-Reasoning, Visual Self-Refinement, Image/Video Caption, Data Curation, ...
◆ Large Language Models (LLMs): Diffusion Language Models, Reinforcement Fine-Tuning, ...
I am always open to discussion and collaboration!
Email: lijinsong0130@gmail.com WeChat: Jinsong0130
Google Scholar Github X/Twitter Linkedin
Publications
( * equal contribution, † corresponding authors )
(Co-) First Author Publications
 |
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Lin Chen*, Xilin Wei*, Jinsong Li*, Xiaoyi Dong*, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Bin Lin, Zhenyu Tang, Li Yuan, Yu Qiao, Dahua Lin, Feng Zhao, Jiaqi Wang NeurIPS 2024 (D&B Track) | Paper | Project Page |  |
|
 |
Are We on the Right Way for Evaluating Large Vision-Language Models?
Lin Chen*, Jinsong Li*, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, Feng Zhao NeurIPS 2024 | Paper | Project Page |  |
Ranked 9th in "Most Influential NIPS 2024 Papers" (15/4043) |
 |
ShareGPT4V: Improving Large Multi-modal Models with Better Captions
Lin Chen*, Jinsong Li*, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, Dahua Lin ECCV 2024 | Paper | Project Page |  |
Ranked 4th in "Most Influential ECCV 2024 Papers" (15/2395) |
Co-Author Publications
 |
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
Long Xing, Qidong Huang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Jinsong Li, Shuangrui Ding, Weiming Zhang, Nenghai Yu, Jiaqi Wang, Feng Wu, Dahua Lin arXiv 2025 | Paper |  |
|
 |
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
Yubo Ma, Jinsong Li, Yuhang Zang, Xiaobao Wu, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Jiaqi Wang, Yixin Cao, Aixin Sun ACL 2025 (Findings) | Paper | 
|
 |
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Yujie Zhou*, Jiazi Bu*, Pengyang Ling*, Pan Zhang, Tong Wu, Qidong Huang, Jinsong Li, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Anyi Rao, Jiaqi Wang, Li Niu ICCV 2025 | Paper | Project Page |  |
|
 |
Half-Xor: A Fully-Dynamic Sketch for Estimating the Number of Distinct Values in Big Tables
Pinghui Wang, Dongdong Xie, Junzhou Zhao, Jinsong Li, Zhicheng Li, Rundong Li, Yang Ren TKDE 2024 | Paper |  |
|
Selected Experiences
 |
Shanghai AI Laboratory
Research Intern Topic: Large Multi-modal Models Mentor: Dr. Jiaqi Wang |
Shanghai, China
Aug, 2023 - Present |
Selected Awards
| ◆ NeurIPS Scholar Award, NeurIPS Foundation | 2024 |
| ◆ Postgraduate Studentship Award, The Chinese University of Hong Kong | 2024 - 2028 |
| ◆ Outstanding Graduate, Xi'an Jiaotong University | 2024 |
| ◆ National 1st Prize, RoboCup China Open | 2022 |
| ◆ National Scholarship × 2, Ministry of Education of PRC | 2021, 2022 |
| ◆ Outstanding Student Award × 3, Xi'an Jiaotong University | 2021, 2022, 2023 |
Selected Services
Academic Reviewer| ◆ NeurIPS 2025 |
| ◆ ENGG1110B Problem Solving by Programming, The Chinese University of Hong Kong | 2024 Fall |
| ◆ IERG2080 Introduction to Systems Programming, The Chinese University of Hong Kong | 2025 Spring |