huang.hengguan@u.nus.edu
Embedded Files
I am Hengguan Huang, an Assistant Professor in the Department of Public Health, Section for Health Data Science and AI, University of Copenhagen. I am also part of the Machine Learning & Global Health Network, where I work closely with Prof. Samir Bhatt and Prof. David Duchêne.
I lead the Scientific AI Group, which aims to advance trustworthy and self-evolving scientific agentic systems by bridging large language models, Bayesian deep learning, and core scientific principles. Our research is highly interdisciplinary, spanning natural language processing, computer vision, and scientific machine learning, with a particular emphasis on public health applications.
My vision is to pioneer AI technologies that are not only driven by big data and large models but are also deeply rooted in scientific principles and aligned with societal values.
Methodological Focus:
Structured and Mechanistic Bayesian Reasoning
Agentic Scientific Discovery
Biological Multimodal LLMs
Safety and Trustworthiness
Research Group Focus:
Trustworthy Agentic System for Public Health
Bio-societal Mechanism Discovery across Bio-medical, Brain, and Population Health Data
!! I am always open to collaborations in any form—be it research partnerships, interdisciplinary projects, or mentoring enthusiastic students. Feel free to reach out if you share similar interests or wish to explore new ideas. !!
Selected Publication
*: first co-author
_: corresponding author
Hengguan Huang, Xiangmin Gu, Hao Wang, Chang Xiao, Hongfu Liu, Ye Wang, Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation, NeurIPS, 2022. [paper][code][appendix]
Hengguan Huang, Hongfu Liu, Hao Wang, Chang Xiao, Ye Wang, STRODE: Stochastic Boundary Ordinary Differential Equation, ICML, 2021. [paper][code][appendix][video]
Hengguan Huang, Fuzhao Xue, Hao Wang, Ye Wang, Deep Graph Random Process for Relational-Thinking-Based Speech Recognition, ICML, 2020. [paper][code][appendix][video]
Hengguan Huang, Hao Wang and Brian Mak, Recurrent Poisson Process Unit for Speech Recognition, AAAI, 2019, Hawaii, USA. [paper][code][appendix]
Xing Shen, Justin Szeto, Mingyang Li, Hengguan Huang, and Tal Arbel. Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification, MICCAI, 2025. [paper][code][appendix]
Xing Shen, Hengguan Huang, Brennan Nichyporuk, Tal Arbel. Improving Robustness and Reliability in Medical Image Classification with Latent-Guided Diffusion and Nested-Ensembles, IEEE Transactions on Medical Imaging, 2025. [paper][code][appendix]
Hengguan Huang*, Songtao Wang*, Hongfu Liu, Hao Wang, Ye Wang. Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset, Findings of the Association for Computational Linguistics: ACL 2024. [paper][code][appendix]
Wei Wei*, Hengguan Huang*, Xiangming Gu, Hao Wang, and Ye Wang. Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization. Transactions of Machine Learning Research. 2022. [paper][code][appendix]
Hengguan Huang*, Xing Shen*, Hao Guangyuan, Songtao Wang, Lingfa Meng, Dianbo Liu, David Alejandro Duchene, Hao Wang, Samir Bhatt. BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling, AAAI, 2026.
Liu Hongfu, Hengguan Huang, Hao Wang, Xiangming Gu, and Ye Wang. On Calibration of LLM-based Guard Models for Reliable Content Moderation, ICLR, 2025. [paper][code][appendix][video]
Liu Hongfu, Hengguan Huang, Ye Wang. Advancing Test-Time Adaptation in Wild Acoustic Test Settings, EMNLP, 2024. [paper][code][appendix][video]
Xueyang Wu*, Hengguan Huang*, Youlong Ding, Hao Wang, Ye Wang, Qian Xu. FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation, AAAI, 2023. [paper][code][appendix][video]
Page updated
Google Sites
Report abuse