---

Dr. Kaiyang Zhou is an Assistant Professor at the Department of Computer Science, Hong Kong Baptist University, working on computer vision and machine learning. He has published more than 30 technical papers in top-tier journals and conferences in relevant fields, including CVPR, ICCV, ECCV, NeurlPS, ICLR, ICML, AAAI, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), and International Journal of Computer Vision (IJCV), with over 9,000 citations received in total. He is an Associate Editor of IJCV, the flagship journal in computer vision, and regularly serves as area chair and senior program committee for top-tier computer vision and machine learning conferences, such as NeurIPS, CVPR, ECCV, and AAAI. He is also the creator of several impactful AI software packages, such as Torchreid (the No.1 popular person re-identification project on GitHub), Dassl (a multifunctional machine learning framework), and CoOp (a prompt learning tool for improving vision-language models). Prior to joining HKBU, he was a postdoc at Nanyang Technological University, Singapore, working with Prof. Ziwei Liu and Prof. Chen Change Loy. He received his PhD in computer science from the University of Surrey, UK, under the supervision of Prof. Tao Xiang.

Fields of specialization: multimodal models, domain generalization, domain adaptation.

To prospective students: I have multiple openings for PhD/RA with topics in LLM & VLM. If you are interested in joining my lab, please email me with your CV, transcripts, and other relevant material. You are highly recommended to contact me via email and receive my endorsement before submitting a formal PhD application to the Department. Due to the large volume of emails, I will only reply to shortlisted candidates.

News & Activities

• [2024-06] Invited to serve as AAAI 2025 senior program committee.
• [2024-06] We're organizing a workshop on Prompting in Vision at CVPR 2024.
• [2024-05] Invited to serve as BMVC 2024 area chair.
• [2024-04] Call for Papers: ECCV 2024 Workshop on Green Foundation Models.
• [2024-04] Invited to serve as NeurIPS 2024 area chair.
• [2024-02] Call for Papers: CVPR 2024 Workshop on Prompting in Vision.
Older News & Activities
[2023-12] Invited to serve as ECCV 2024 area chair.
[2023-10] Gave a talk at VALSE.
[2023-08] Gave a talk at AIGC-2023 Workshop on Trustworthy Foundation Models under Imperfect Data.
[2023-08] Gave a talk at IJCAI-2023 Symposium Session on Medical Large Models.
[2023-08] Invited to serve as CVPR 2024 area chair.
[2023-08] Invited to join the editorial board of International Journal of Computer Vision as associate editor.
[2023-07] Gave a talk at the University of Tokyo (slides & video).
[2023-06] We're organizing a tutorial on Prompting in Vision at CVPR 2023.
[2023-01] Call for Papers: ICLR 2023 workshop on what do we need for successful domain generalization?
[2022-09] Call for Papers: IJCV Special Issue on The Promises and Dangers of Large Vision Models.

Professional Services

• Associate Editor: International Journal of Computer Vision (IJCV)
• Guest Editor: IJCV Special Issue on The Promises and Dangers of Large Vision Models
• Area Chair / Senior Program Committee: NeurIPS, CVPR, ECCV, BMVC, AAAI
• Organizing Committee: The AI Talks, CVPR'23 Tutorial on Prompting, ICLR'23 Workshop on DG, CVPR'24 Workshop on Prompting, ECCV'24 Workshop on Green Foundation Models
• Reviewer: TPAMI, IJCV, ICLR, NeurIPS, ICML, AAAI, CVPR, ICCV, ECCV, etc.

Mentoring

• Jiaer Xia (PhD, 2024-present)
• Sifeng Shang (PhD, 2024-present)
• Bingkui Tong (RA, 2024-present)

Teaching

• Hong Kong Baptist University
  COMP7065: Innovative Laboratory
  ITS 7010: ITS Doctoral Research Training I
• Nanyang Technological University
  AI6126 Guest Lecture: Open-World Visual Recognition
  OpenMMLab Workshop: Object Detection
• Queen Mary University of London
  ECS797: Machine Learning for Visual Data Analytics
  ECS708: Machine Learning

Software & Datasets

• Torchreid: A codebase for person re-identification (including documentation and model zoo).
• Dassl: A multifunctional codebase for domain generalization, domain adaptation and semi-supervised learning.
• CoOp: A codebase for developing adaptation methods (e.g., prompt learning) for large-scale vision-language models.
• OpenOOD: A codebase and benchmark for out-of-distribution detection.
• PSG: A dataset for panoptic scene graph generation. (Codebase: OpenPSG.)