About Me
I am currently a third-year Ph.D. student at Tianjin Key Laboratory of Visual Computing and Intelligent Perception (VCIP), Nankai University, advised by Prof. Xiang Li and Prof. Jian Yang. I am also a research intern at Alibaba DAMO Academy, led by Dr. Yibing Song and Dr. Fan Wang. My research mainly focuses on vision-language models, multi-modal learning and efficient model computing.
The code of my research work will be open-source, and I will also attach a detailed Chinese interpretation of the paper. Although the interpretation may be somewhat fragmented, I will do my best to present the insights and ideas behind the paper.
I am also maintaining a curated list [Links] of prompt learning methods for vision-language models. Feel free to check it out~
The journey of scientific research is challenging, but I’m passionate about my work. If you’re interested in my research or encounter any problems, please contact me via email (zhengli97[at]qq.com).
Educations
- 2022 - Present. Ph.D., Computer Science and Technology, Nankai University.
- 2019 - 2022. M.Eng., Computer Applied Technology, Hangzhou Normal University.
- 2015 - 2019. B.Eng., Communication Engineering, North China University of Science and Technology.
Experiences
- 2024.05 - Present. Alibaba DAMO Academy, Hangzhou. Research Intern.
- 2023.09 - 2024.05. Ant Group, Hangzhou. Research Intern. Led by Xinyi Fu and Dr. Xing Fu.
- 2021.10 - 2023.08. Megvii Research, Nanjing. Research Intern. Led by Renjie Song.
Publications
[CVPR 2024]
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models.
Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang.
[Paper][Code][Project Page][中文解读]
PromptKD is a simple and effective prompt-driven unsupervised distillation framework for VLMs, with state-of-the-art performance.
[AAAI 2023]
Curriculum Temperature for Knowledge Distillation.
Zheng Li, Xiang Li, Lingfeng Yang, Borui Zhao, Renjie Song, Lei Luo, Jun Li, Jian Yang.
[Paper][Code][Project Page][中文解读]
CTKD organizes the distillation task from easy to hard through a dynamic and learnable temperature.
The temperature is learned during the student’s training process with a reversed gradient that aims to maximize the distillation loss.
[ICCV 2021]
Online Knowledge Distillation for Efficient Pose Estimation.
Zheng Li, Jingwen Ye, Mingli Song, Ying Huang, Zhigeng Pan.
[Paper][Code][Project Page][中文解读]
OKDHP first proposes to distill the pose structure knowledge in a one-stage manner. The FAU module integrates students from multiple branches into one teacher, which then distills the student branches in reverse.
[ACCV 2020]
Online Knowledge Distillation via Multi-branch Diversity Enhancement.
Zheng Li, Ying Huang, Defang Chen, Tianren Luo, Ning Cai, Zhigeng Pan.
[Paper]
OKDMDE is a simple and effective technique to enhance model diversity in online knowledge distillation.
-
[ECCV 2024] Cascade Prompt Learning for Vision-Language Model Adaptation.
Ge Wu, Xin Zhang, Zheng Li, Zhaowei Chen, Jiajun Liang, Jian Yang, Xiang Li.
[Paper] [Code] -
[CVIU 2023] GEIKD: Self-knowledge Distillation based on Gated Ensemble Networks and Influences-based Label Noise Removal.
Fuchang Liu, Yu Wang, Zheng Li, Zhigeng Pan.
[Paper]
Competitions
- Kaggle Competition Master. 2 Gold Medals. [My Profile]
Review Services
- 2022 - Present. AAAI, ECCV, CVPR, ICML, NeurlPS, ICLR, IJCV, TIP, KBS, TNNLS…
Personal Hobbies
- Photography 📸. I am a contracted photographer for 500px Gallery. Some photos I took while traveling and mountaineering.
- Mountaineering 🗻. Summit: Haba Snow Mountain (5396m)
- Trail Running 🏃♂️ (iTRA). TNF100 Ultra Trail Challenge Moganshan - 30km Group. Finish: 5h28min (33km).