Min Zeng

I am Min Zeng, a Postdoctoral Research Associate at University of Minnesota, working with Prof. Rui Zhang. I received my Ph.D. in Electronic and Computer Engineering from HKUST, advised by Prof. Yike Guo, and my Master's degree in Computer Science and Engineering from Shanghai Jiao Tong University, advised by Prof. Yuan Luo.

I welcome collaborations with researchers working on EHR data or continual learning. Feel free to reach out via email.

Research

Medicine never stands still: guidelines are revised, new evidence emerges, and patient records grow with every encounter. I build large language models that keep pace with this change—learning continually from evolving medical knowledge and reasoning over patient data in electronic health records (EHRs)—building on my Ph.D. work in continual learning for NLP.

01

Continual learning: from methods to evolving medical knowledge

Learning new knowledge without catastrophic forgetting: DCL (UAI’24), PCGR (NAACL’25), TCL (NAACL’25 Findings), and SAFM (EACL’26); MedCL-Bench (preprint) for biomedical continual learning; and ChronoEvo (preprint) for evaluating whether LLMs incorporate revised clinical guidelines.

02

Longitudinal reasoning over patient trajectories

Reasoning over patient data that evolves across EHR encounters: EVLU (preprint) for reliably updating clinical judgment as new evidence arrives, and EpiScreen (npj Digital Medicine’26) for early epilepsy detection.

03

Memory for lifelong LLM systems

Deciding what LLM systems should retain, replace, or forget under limited memory, with applications to longitudinal patient records.

News

Selected Publications [Full List]

* Equal contribution.

Recent Preprints

AI for Healthcare

Large language models for digital mental health

Large language models for digital mental health: an HCI-centered scoping review

Min Zeng, Zaifu Zhan, Kai Yu, Chao Zeng, Duzhen Zhang, Shuang Zhou, Yu Hou, Mingquan Lin, Rui Zhang

npj Digital Medicine, 2026 (Impact Factor: 18)

Early epilepsy detection from electronic health records with large language models

Early epilepsy detection from electronic health records with large language models

Shuang Zhou, Kai Yu, Zaifu Zhan, Huixue Zhou, Min Zeng, Feng Xie, Zhiyi Sha, Rui Zhang

npj Digital Medicine, 2026 (Impact Factor: 18)

Multimodal artificial intelligence agents in healthcare: a scoping review

Multimodal artificial intelligence agents in healthcare: a scoping review

Kai Yu, Shuang Zhou, Yu Hou, Yiran Song, Min Zeng, Fangqiao Tian, Jin Du, Wenya Xie, Biao Yin, You Chen, Feifan Liu, Jie Ding, Zirui Liu, Mingquan Lin, Rui Zhang

npj Digital Medicine, 2026 (Impact Factor: 18)

Continual Learning for Language Models

Sparse Adapter Fusion for Continual Learning

Sparse Adapter Fusion for Continual Learning in NLP

Min Zeng*, Xi Chen*, Haiqin Yang, Yike Guo

Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026

Prototype Conditioned Generative Replay for Continual Learning in NLP

Prototype Conditioned Generative Replay for Continual Learning in NLP

Xi Chen*, Min Zeng*

Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025

Task-wrapped Continual Learning in Task-Oriented Dialogue Systems

Task-wrapped Continual Learning in Task-Oriented Dialogue Systems

Min Zeng, Haiqin Yang, Xi Chen, Yike Guo

Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL Findings), 2025

Dirichlet Continual Learning

Dirichlet Continual Learning: Tackling Catastrophic Forgetting in NLP

Min Zeng, Haiqin Yang, Wei Xue, Qifeng Liu, Yike Guo

Conference on Uncertainty in Artificial Intelligence (UAI), 2024

Earlier Work in NLP

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation

Min Zeng, Yisen Wang, Yuan Luo

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019

Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

Holy Lovenia*, Bryan Wilie*, Willy Chung*, Min Zeng*, Samuel Cahyawijaya, Dan Su, Pascale Fung

Proceedings of the 7th Workshop on Representation Learning for NLP (RepL4NLP @ ACL), 2022

RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

Ziwei Ji, Zihan Liu, Nayeon Lee, Tiezheng Yu, Bryan Wilie, Min Zeng, Pascale Fung

Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2023

Services

Conference Area Chair: ARR October 2026 (NAACL 2027), ARR January 2026 (ACL 2026)

Conference Reviewers: ICLR, ACL, EMNLP, NAACL, UAI, EACL

Journal Reviewers: IEEE TASLP, npj Digital Medicine, npj Health Systems

Academic Service: AMIA 2025 NLP Year-in-Review Volunteer