I am currently a Ph.D. candidate at Computer Vision and Machine Intelligence (CVMI) Lab, the University of Hong Kong (HKU), supervised by Prof. Xiaojuan Qi, and a student member of Deep Vision Lab (led by Prof. Jiaya Jia). Before that, I obtained my M.Sc degree at the Department of Computer Science, University of Sheffield (UoS) (supervised by Dr. Li Sun), and my B.Sc degree at the Department (School) of Mathematics, East China University of Science and Technology (ECUST).
My research interests are mainly in 2D/3D Open-World Learning, Out-Of-Distribution (OOD) Detection & Generation, and Multimodal Large Language Models (MLLMs), combined with Representation Learning, Open-World Knowledge, and Synthetic Data. At the same time, I explore the application of machine learning in AI4Science, including Smart Cities, Medical Images, etc.
If you are interested in my topic or paper, please do not hesitate to contact me. I am happy to communicate or create potential cooperation opportunities.
News
- 2025.06: Three papers are accepted by International Conference on Computer Vision (ICCV) 2025.
- 2025.05: I will attend VALSE 2025 (06/06-08/06, Zhuhai, China), see you in Zhuhai!
- 2025.02: One paper is accepted by Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
- 2024.09: I am invited by OOD-CV workshop in ECCV 2024 and will present a talk about Out-of-Distribution Generation at MiCo Milano, Italy (09:50, UTC+2, 30/09/2024). Thanks for the invitation. Welcome to attend and discuss with me!
- 2024.09: I will attend ECCV 2024 (29/09-04/10, Milan, Italy) and present my published paper’s poster, see you in Milan!
- 2024.08: I am invited by the Faculty of Engineering, HKU and will present a Young Scholar TechTalk: “Learning Out-of-Distribution Object Detectors from Foundation Models” at Tam Wing Fan Innovation Wing Two, HKU (16:30, HKT, 16/09/2024). Thanks for the invitation. Welcome to attend and discuss with me!
- 2024.07: One paper is accepted by European Conference on Computer Vision (ECCV) 2024.
- 2024.04: I will attend China 3DV 2024 (19/04-21/04, Shenzhen, China), see you in Shenzhen!
- 2023.06: I will attend CVPR 2023 (18/06-22/06, Vancouver, Canada) and present my published paper’s poster remotely.
- 2023.06: I will attend VALSE 2023 (10/06-12/06, Wuxi, China), see you in Wuxi!
- 2023.02: One paper is accepted by Conference on Computer Vision and Pattern Recognition (CVPR) 2023.
Invited Talks and Reports
- Can Out-of-Distribution Object Detectors Learn from Foundation Models?
Invited Talk, OOD-CV workshop, ECCV 2024 (30/09/2024, link) - Learning Out-of-Distribution Object Detectors from Foundation Models
Young Scholar TechTalk, Tam Wing Fan Innovation Wing Two, HKU (16/09/2024, link) - Building a Plug-in for Autonomous Driving
Paper Reporting, QbitAI (08/2023, link)
Publications and Preprints
Computer Vision and Multimodal LLMs
- Aligning Effective Tokens with Video Anomaly in Large Language Models
Yingxian Chen∗, Jiahui Liu∗, Ruidi Fan, Yanwei Li, Chirui Chang, Shizhen Zhao, Wilton.W.T.Fok, Xiaojuan Qi†, Yik Chung WU†
International Conference on Computer Vision (ICCV) 2025 - Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection
Shizhen Zhao, Jiahui Liu, Xin Wen, Haoru Tan, Xiaojuan Qi†
International Conference on Computer Vision (ICCV) 2025 - How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach
Chirui Chang, Jiahui Liu, Zhengzhe Liu, Xiaoyang Lyu, Yi-Hua Huang, Xin Tao, Pengfei Wan, Di Zhang, Xiaojuan Qi†
International Conference on Computer Vision (ICCV) 2025 - Learning from Neighbors: Category Extrapolation for Long-Tail Learning
Shizhen Zhao, Xin Wen, Jiahui Liu, Chuofan Ma, Chunfeng Yuan, Xiaojuan Qi†
Conference on Computer Vision and Pattern Recognition (CVPR) 2025 - Can OOD Object Detectors Learn from Foundation Models?
Jiahui Liu, Xin Wen, Shizhen Zhao, Yingxian Chen, Xiaojuan Qi†
European Conference on Computer Vision (ECCV) 2024 - Can 3D Vision-Language Models Truly Understand Natural Language?
Weipeng Deng, Jihan Yang, Runyu Ding, Jiahui Liu, Yijiang Li, Xiaojuan Qi, Edith Ngai
Arxiv 2024 - MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds
Jiahui Liu∗, Chirui Chang∗, Jianhui Liu, Xiaoyang Wu, Lan Ma, Xiaojuan Qi†
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
AI for Science
Academic and Community Services
- Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, IROS, 3DV, ACM MM, etc.
- Journal Reviewer: IEEE TIP, Pattern Recognition, etc.
- Workshop Committee / Reviewer:
- Contribute to Open Source Community: Open-mmlab / MMDetection
Life and Hobbies
- I am a senior football fan and was qualified as a National Level-2 Football Referee by Chinese Football Association, advised by Jianpin Lu and Di Wang. I have served as the referee for the Shanghai Youth Football Series, the Northern Ireland Southeast Asian Student Games, etc.
- I like different styles of music and have passed Piano Level-10 test of Chinese Musicians’ Association.
- I like the delicacies from different regions and the cultures behind them, and I’m trying to record and understand them.