Hi, I am Xue Jiang, a joint Ph.D. student at the Trustworthy Machine Learning and Reasoning (TMLR) Group, Department of Computer Science, Hong Kong Baptist University, advised by Prof. Bo Han, and Southern University of Science and Technology, advised by Prof. Feng Zheng. In the TMLR Group, I am also co-supervised by Prof. Feng Liu and work closely with Dr. Zhen Fang. From Feb. to Aug. 2025, I visited RIKEN AIP, working with Prof. Masashi Sugiyama and Dr. Gang Niu.
My research focuses on building reliable and trustworthy machine learning systems, with particular interests in out-of-distribution detection, as well as hallucination mitigation and safety for multimodal large language models.
Please feel free to email me for research, collaborations, or a casual chat.
Educations
- 2022.09 - present, Southern University of Science and Technology (SusTech) & Hong Kong Baptist University (HKBU), Ph.D. in Computer Science.
- 2019.09 - 2022.06, Wuhan University, M.E. in Computer Science.
- 2015.09 - 2019.06, Wuhan University, B.E. in Electronic Information Engineering.
Selected Publications
* indicates equal contribution; full list can refer to Google Scholar.
-
Feature Map Matters in Out-of-Distribution Detection [PDF]IEEE Transactions on Pattern Analysis and Machine Intelligence
-
Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach [PDF]Proceedings of the AAAI Conference on Artificial Intelligence
-
MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue [PDF]International Conference on Machine Learning
-
Negative Label Guided OOD Detection with Pretrained Vision-Language Models [PDF]International Conference on Learning Representations
-
Detecting Out-of-Distribution Data through In-Distribution Class Prior [PDF]International Conference on Machine Learning
-
REVERIE+: Generalized Reflective Instruction Tuning for Hallucination Mitigation in Advanced VLMs [PDF]International Journal of Computer Vision
-
On the Generalization Ability of Next-Token-Prediction Pretraining [PDF]International Conference on Machine Learning
-
On the Stability and Generalization of Triplet Learning [PDF]Proceedings of the AAAI Conference on Artificial Intelligence
-
Cross-Image Relational Knowledge Distillation for Semantic Segmentation [PDF]IEEE/CVF Conference on Computer Vision and Pattern Recognition
Honors and Awards
- 2026, Gold Reviewer Award, ICML.
- 2024, Outstanding Reviewer Award, NeurIPS.
- 2024, Best Research Performance Award, HKBU.
- 2023, Research Excellence Award, HKBU.
Services
- Conference Reviewer for ICML, NeurIPS, ICLR, AAAI, CVPR.
- Journal Reviewer for TPAMI, Neural Networks, TNNLS, IJCV, TMLR.
Teaching
- 2024 Spring, TA for CS308: Computer Vision, SusTech.
- 2023 Fall, TA for CS205: C/C++ Program Design, SusTech.
- 2019 Fall, TA for Fundamentals of Circuit and Electronics, WHU.
Experiences
- 2025.02 - 2025.08, Visiting Researcher at RIKEN Center for Advanced Intelligence Project (AIP), hosted by Prof. Masashi Sugiyama and Dr. Gang Niu.
- 2021.05 - 2021.12, Internship at Horizon Robotics, focusing on self-supervised learning for object detection.