Web Analytics

Jun Zhang

prof_pic.jpg

I am a second-year master’s student in MCG Group, Department of Computer Science and Technology, Nanjing University, under the supervision of Prof. Limin Wang. I received a bachelor degree in Computer Science and Technology in Nanjing University in 2023.

Currently, I am a research intern in Tencent ARC lab, working on Multimodal Large Language Models (MLLMs).

I am actively seeking Job/PhD opportunities! Feel free to reach out if you think we might be a good fit.

news

Dec 20, 2025
:fire: 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]
Jun 26, 2025
:tada::tada::tada: p-MoD is accepted by ICCV 2025!
Dec 6, 2024
:fire: We present p-MoD, efficient MLLMs built with Mixture-of-Depths mechanism.
Sep 1, 2023
I am officially enrolled as a master’s student! :smile:

selected publications

2025

  1. arXiv 2025
    TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
    Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, and Limin Wang
    arXiv preprint, 2025
    arXiv Code Website
  2. ICCV 2025
    p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
    ICCV, 2025
    arXiv Code
  3. arXiv 2025
    VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking
    arXiv preprint, 2025
    arXiv

experience

Research Intern, ARC Lab, Tencent
Research Intern, ARC Lab, Tencent
2025.03 - Present
Shenzhen, China

Working on MLLMs with Dr. Yixiao Ge, Dr. Teng Wang and Dr. Yuying Ge.