Jun Li 李俊

I am a first-year Ph.D. student at the University of Hong Kong (HKU), advised by Prof. Xiaojuan Qi.

My research interests are embodied intelligence, foundation models, and vision-language models (VLMs).

I received my B.E. from Harbin Institute of Technology in 2021 and my master’s degree from the Institute of Automation, Chinese Academy of Sciences (CASIA) in 2024. At CASIA, I was advised by Prof. Jun Wan and worked closely with Prof. Zhen Lei (IEEE Fellow).

Previously, I worked at Kuaishou Technology and ByteDance, focusing on frontier research and real-world applications of Multimodal Large Language Models. I also interned with the Foundation Model Group at Megvii Research, advised by Xiangyu Zhang.

• Embodied Intelligence
• Foundation Model
• VLM

lijun9066@outlook.com · Publications on Google Scholar

News

• 2026.09: I joined the University of Hong Kong as a Ph.D. student!
• 2025.12: I joined ByteDance!
• 2025.05: One paper was accepted by TNNLS.
• 2025.03: One paper was accepted by CVPR 2025.
• 2024.07: I joined Kuaishou Technology!

Publications

TCSVT 2026

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

Hao Tan, Zichang Tan, Jun Li, Jun Wan, Zhen Lei, Stan Z. Li

PDF

CVPR 2025

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

Hao Tan, Zichang Tan, Jun Li, Ajian Liu, Jun Wan, Zhen Lei

PDFProject

— stars — forks

TNNLS 2025

UBG: An Unreal BattleGround Benchmark With Object-Aware Hierarchical Proximal Policy Optimization

Longyu Niu, Baihui Li, Xingjian Fan, Hao Fang, Jun Li, Junliang Xing, Jun Wan, Zhen Lei

PDF

AAAI 2024

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

Hao Tan*, Jun Li*, Yizhuang Zhou, Jun Wan, Zhen Lei, Xiangyu Zhang

PDFProject

— stars — forks

COLING 2024

Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation

Zhigang Chen, Benjia Zhou, Jun Li, Jun Wan, Zhen Lei, Ning Jiang, Quan Lu, Guoqing Zhao

PDF

ICLR 2023

Reversible Column Networks

Yuxuan Cai, Yizhuang Zhou, Qi Han, Jianjian Sun, Xiangwen Kong, Jun Li, Xiangyu Zhang

PDFIntroductionProject

— stars — forks

Pattern Recognition

NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition

Zichang Tan*, Jun Li*, Jinhao Du, Jun Wan, Zhen Lei, Guodong Guo

PDFProject

— stars — forks

TIP

General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone

Zenghao Bao, Zichang Tan, Jun Li, Jun Wan, Xibo Ma, Zhen Lei

PDF

CVPR 2022

Nested Collaborative Learning for Long-Tailed Visual Recognition

Jun Li*, Zichang Tan*, Jun Wan, Zhen Lei, Guodong Guo

PDFProject

— stars — forks

* Equal contribution.

Honors & Awards

• 2022.12 National Scholarship.
• 2021.06 Outstanding Graduates of Harbin Institute of Technology.
• 2021.05 New Engineering Program Design Ability Examination (Level A), Rank 1/2280.

• 2019.08 National First Prize in the National College Student “NXP Cup” Intelligent Vehicle Contest. Watch on Bilibili — views

• 2019.12 First Prize in the Heilongjiang Province Division of the National College Student Mathematical Modeling Competition.
• 2016.11 National Olympiad in Informatics in Provinces (NOIP) - Advanced Group, Second Prize.

Education

• 

  The University of Hong Kong

  Ph.D.

  2026.09 – 2030.09 (expected)

  Hong Kong, China

• 

  Institute of Automation, Chinese Academy of Sciences

  Master's degree

  2021.08 – 2024.07

  Beijing, China

• 

  Harbin Institute of Technology

  Bachelor of Engineering (B.E.)

  2017.08 – 2021.06

  Harbin, China

Work Experience

• 

  ByteDance

  2025.12 – 2026.08

• 

  Kuaishou Technology

  2024.07 – 2025.09

Internships

• 

  Megvii Research

  Algorithm Intern

  2022.07 – 2023.12

  Advisor: Xiangyu Zhang

Talks

• 2022.12, presentation on the paper “Nested Collaborative Learning for Long-Tailed Visual Recognition” at VALSE2022.