Xiaoguang Zhu
 |
Postdoctoral Researcher, |
Biography
I am currently a Postdoctoral Researcher at UC Davis, working on causal and multimodal learning for medical AI. My mentors include Prof. Vladimir Filkov, Prof. Chen-Nee Chuah, Prof. Uma Srivatsa, and Prof. Nipavan Chiamvimonvat.
I received my PhD in Information and Communication Engineering from Shanghai Jiao Tong University (SJTU) in 2022, advised by Prof. Peilin Liu. I also obtained my Master’s and Bachelor’s degrees from SJTU.
My research focuses on building robust and interpretable learning systems for healthcare and multimodal AI.
Research Interests
Causal Deep Learning for Health
Multimodal Learning
Multimodal Large Language Models
Representation Learning
AI for Cardiovascular Disease
News
Dec. 2025: Work on cardiac sarcoidosis progression modeling and atrial fibrillation medication outcome estimation is submitted to Heart Rhythm 2026.
Dec. 2025: Our work on Privacy-Preserving Video Anomaly Detection: A Survey is accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS).
Nov. 2025: Work on Causality-Aware Direct Preference Optimization for Aligning Medical Vision-Language Models is submitted to CVPR 2026.
Nov. 2025: Work on Empowering Source-Free Domain Adaptation with MLLM-Driven Curriculum Learning is accepted by WACV 2026.
Oct. 2025: Work on Graph-Based Neural Controlled Diffusion Equations for Atrial Fibrillation Outcome Prediction Using Intracardiac Electrogram is submitted to ICASSP 2026.
Oct. 2025: Work on Benchmarking Parameter-Efficient Adaptation of Vision-Language Models on Pathology is accepted at the NeurIPS 2025 Workshop on Imageomics.
Sep. 2025: Work on Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities is submitted to IEEE TKDE.
Sep. 2025: Work on Co-HSF: Resource-Efficient One-Shot Semi-Supervised Adaptation of Histopathology Foundation Models is accepted at the AAAI 2025 Spring Symposium on AI for Health.
Aug. 2025: Work on Multimodal Large Language Models in Medicine and Nursing: A Survey is submitted to IEEE Reviews in Biomedical Engineering.
Jun. 2025: Work on CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos appears in IEEE Transactions on Image Processing, Volume 34.
Dec. 2024: Work on Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning is accepted by ICME 2025.
Apr. 2024: Joined UC Davis DataLab as a Postdoctoral researcher, focusing on causal and multimodal learning for medical AI.
Apr. 2024: Work on Supplementing Missing Visions via Dialog for Scene Graph Generation is published at ICASSP 2024.
Jan. 2024: Work on Graph-based Networks with Channel Selection for EEG Signal Learning is published in Biomedical Signal Processing and Control.
Academic Experience
Invited Reviewer: CVPR 2021-2026, ICCV 2021-2025, ECCV 2022-2024, AAAI 2025, IEEE Signal Processing Letters, ACM Computing Surveys, Artificial Intelligence Reviews
Technical Program Committee: INSAI 2021-2025
Guest Editor: Special Issue on Action Recognition, Journal of Imaging
Teaching Assistant: Digital Circuits, Shanghai Jiao Tong University, 2015