I am currently a first-year Ph.D. student in Computer Vision and Machine Learning Group at University of Illinois Urbana-Champaign, advised by Prof. Yaoyao Liu and Prof. Yingying Li. Before that, I recieved a Master’s degree at the College of Computer Science, Nankai University, supervised by Prof. Xialei Liu, and I received my bachelor’s degree from College of Cyberspace Security, Nankai University.
My current research interests lie in enhancing models’ adaptability to complex, real-world environments and empowering them with human-like capabilities for lifelong knowledge acquisition. Specifically, my research focuses on:
- Continual Learning: Continuously expanding the boundaries of model capabilities across sequential tasks while overcoming the catastrophic forgetting of previously acquired knowledge.
- Self-evolving Agent: Enabling agents and foundation models to summarize experiences and evolve within their environments, achieved through memory mechanisms and representation learning.
If you’re interested in my research or have any research-related questions, please feel free to contact me via email at haorilu2 [at] illinois.edu or luhaori2001 [at] gmail.com.
📝 Publications
Haori Lu, Xusheng Cao, Linlan Huang, Enguang Wang, Fei Yang, Xialei Liu
Bridging Inter-task Gap of Continual Self-supervised Learning with External Data
Haori Lu, Xusheng Cao, Linlan Huang, Enguang Wang, Fei Yang, Xialei Liu
Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
Xusheng Cao, Haori Lu, Linlan Huang, Fei Yang, Xialei Liu, Ming-Ming Cheng
Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-based Continual Learning
Linlan Huang, Xusheng Cao, Haori Lu, Yifan Meng, Fei Yang, Xialei Liu
Class Incremental Learning for Image Classification with Out-of-Distribution Task Identification
Xusheng Cao, Haori Lu, Xialei Liu, Ming-Ming Cheng
Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion
Linlan Huang, Xusheng Cao, Haori Lu, Xialei Liu
Generative Multi-modal Models are Good Class Incremental Learners
Xusheng Cao, Haori Lu, Linlan Huang, Xialei Liu, Ming-Ming Cheng
🎖 Honors and Awards
- 2024.01 Champaign of 2nd Greater Bay Area International Algorithm Case Competition – Continual Learning Track
📖 Educations
- 2026.08 - Present, Ph.D. in Information Sciences, University of Illinois Urbana-Champaign, Illinois, USA.
- 2023.09 - 2026.06, M.S. in Computer Technology, Nankai University, Tianjin, China.
- 2019.09 - 2023.06, B.S. in Information Security and Law, Nankai University, Tianjin, China.
💻 Internships
- 2025.04 - 2025.09, XPENG Autonomous, Beijing, China, Mentor: Xuanyi Li.
💬 Services
Reviewer:
- Conference: CVPR, ICCV, ECCV, ICML, BMVC
- Journal: IJCV