Preprints

*:  first co-author

_: corresponding author

• Hengguan Huang, et al. Verbalized Probabilistic Graphical Modeling. (Submitted)

• Xueyang Wu*, Hengguan Huang*, Hao Wang, Ye Wang, Qian Xu,  EP-GAN: Unsupervised Federated Learning with Expectation-Propagation Prior GAN.

 Journal papers

2025

• 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]

2022

• 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]

 Conference papers

2025

• 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]

• 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]

2024

• Liu, Hongfu, Hengguan Huang, Ye Wang. Advancing Test-Time Adaptation in Wild Acoustic Test Settings, EMNLP, 2024

• 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] 

• Guang-Yuan Hao, Hengguan Huang, Haotian Wang, Jie Gao, Hao Wang, Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees, AAAI, 2024. [paper][code][appendix] 

2023

• 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] (Oral)

2022

• 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]

• 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]

2021

• Hengguan Huang, Hongfu Liu, Hao Wang, Chang Xiao, Ye Wang, STRODE: Stochastic Boundary Ordinary Differential Equation, ICML, 2021. [paper][code][appendix]

2020

• Hengguan Huang, Fuzhao Xue, Hao Wang, Ye Wang, Deep Graph Random Process for Relational-Thinking-Based Speech Recognition, ICML, 2020. [paper][code][appendix]

2019

• Hengguan Huang, Hao Wang and Brian Mak, Recurrent Poisson Process Unit for Speech Recognition, AAAI, 2019, Hawaii, USA. [paper][code][appendix] (Spotlight)

2015-2018

• Huang, Hengguan, and Brian Mak, WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition", IEEE ISCSLP 2018, Taiwan. (Oral)

• Hengguan Huang and Brian Mak, To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-order Feedback From Multiple Histories, ISCA Interspeech, 2017, Stockholm, Sweden.

• Hengguan Huang and Khe Chai Sim, An Investigation of Augmenting Speaker Representations to Improve Speaker Normalization for DNN-based Speech Recognition, IEEE ICASSP 2015, Brisbane, Sydney. 

PhD Thesis

BRAIN-INFORMED ARTIFICIAL INTELLIGENCE: RANDOM GRAPHS, DYNAMICAL SYSTEMS AND BEYOND ,  [PhD Thesis Award honorable mentions]