Jun Zhang
I am a Researcher/Engineer at Joy Future Academy (京东探索研究院) through the TGT (Tech Genius Team) Program, working with Qingyi Si and Jiaqi Wang, focusing on Multimodal Large Language Models (MLLMs) and Video Understanding.
I received my B.S. and M.S. degrees in Computer Science and Technology from Nanjing University, in 2023 and 2026, respectively. I was a member of the MCG Group, advised by Prof. Limin Wang.
Previously, I was an intern in the Foundation Model Team at StepFun, and before that, a research intern at Tencent ARC Lab. In both internships, I worked on Multimodal Post-training (SFT & RL) and Video Understanding.
We are currently hiring for both full-time and internship positions for the TGT program, focusing on MLLMs and Video Understanding. Please feel free to reach out if you are interested!
news
We released Step 3.7 Flash. 
TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs is accepted by CVPR 2026! [Website] Check our new paper TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs. We expose critical quality issues in existing VTG benchmarks and propose quality-assured datasets for both training and evaluation. Building upon reliable data, we explore algorithmic designs and release state-of-the-art open-source grounding models. [Website] selected publications
2026
2025
- arXiv 2025VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured ThinkingarXiv preprint, 2025
experience
Researcher/Engineer, Joy Future Academy
Working on multimodal large language models and video understanding through the TGT (Tech Genius Team) Program with Qingyi Si and Jiaqi Wang.
Intern, Foundation Model Team, StepFun
Worked on multimodal post-training and video understanding at StepFun.
Research Intern, Tencent ARC Lab
Worked on multimodal post-training and video understanding with Dr. Yixiao Ge, Dr. Teng Wang, and Dr. Yuying Ge.