|
Jialiang Wang 王嘉良Ph.D. student
Harbin Institute of Technology
Email: cswjl@stu.hit.edu.cn |
Biography
Hi! I am a joint Ph.D. student in Computer Science at Harbin Institute of Technology (HIT) and City University of Hong Kong (CityUHK), advised by Prof. Xianming Liu and Prof. Haoliang Li. I received my B.Eng. from Dalian University of Technology in 2023.
My research interest is Trustworthy Machine Learning, especially learning with imperfect data and LLM post-training. Please contact me if you'd like to discuss with me.
Education
|
City University of Hong Kong |
Sep. 2025 - present |
|
Harbin Institute of Technology |
Sep. 2023 - present |
|
Dalian University of Technology |
Sep. 2019 - Jun. 2023 |
Publications
|
Unbiased Alignment for Large Language Models with Noisy Preferences Jialiang Wang, Xianming Liu, Xiong Zhou, Hui Liu, Haoliang Li International Conference on Machine Learninqg (ICML 2026) |
|
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition Hui Liu, Kecheng Chen, Jialiang Wang, Xianming Liu, Wenya Wang, Haoliang Li The Conference on Computer Vision and Pattern Recognition (CVPR 2026) |
|
Variation-Bounded Loss for Noise-Tolerant Learning Jialiang Wang*, Xiong Zhou*, Xianming Liu, Gangfeng Hu, Deming Zhai, Junjun Jiang, Xiangyang Ji, Haoliang Li The AAAI Conference on Artificial Intelligence (AAAI 2026) |
|
Joint Asymmetric Loss for Learning with Noisy Labels Jialiang Wang, Xianming Liu, Xiong Zhou, Gangfeng Hu, Deming Zhai, JunJun Jiang, Xiangyang Ji International Conference on Computer Vision (ICCV 2025) |
|
\(\epsilon\)-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise Jialiang Wang*, Xiong Zhou*, Deming Zhai, Junjun Jiang, Xiangyang Ji, Xianming Liu Annual Conference on Neural Information Processing Systems (NeurIPS 2024) |
|
Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data Xiong Zhou, Xianming Liu, Hao Yu, Jialiang Wang, Zeke Xie, Junjun Jiang, Xiangyang Ji International Conference on Learning Representations (ICLR 2024) |
Services
- Reviewer: NeurIPS, ICLR, ICML, etc.
- ICML 2026 Gold Reviewer
Selected Awards
- Outstanding graduate of Dalian University of Technology, 2023
- Tencent Scholarship, 2025
Last update: Jun. 2026