.01

About

Hi! I am a Ph.D. student in Computer Science at the University of Georgia, advised by Dr. Fei Dou. Previously, I was a research assistant at the Hong Kong University of Science and Technology with Prof. Dit-Yan Yeung. I received my M.Sc. from University College London and B.Sc. from the University of Liverpool.

I build evidence-grounded and explainable AI for clinical diagnosis and health sensing: models that read physiological signals (ECG, PPG, BCG, BSG) and clinical records, acquire the evidence they need, and reason to a diagnosis that a clinician can audit.

CV / Resume Google Scholar

Latest News

• 2026/09/24: Our paper DeepArrhythmia on evidence-acquiring ECG arrhythmia classification is accepted to NeurIPS 2026!
• 2026/07/30: Released EarlyDx, an admission-anchored benchmark for evidence-supported ED diagnosis.
• 2026/06/15: Peak-Detector, explainable peak detection with instruction-tuned LLMs, is published in ACM IMWUT (UbiComp) 2026.
• 2026/05/10: ADLGen (co-first author) is published in the proceedings of ACM SenSys 2026.
• 2024/08/14: Started my Ph.D. in Computer Science at the University of Georgia with Dr. Fei Dou.

Fun Fact

🃏 Outside research, I was one of the top players in the trading card game Legends of Runeterra, and represented the UK at LoR Masters Europe, Riot Games' official European tournament.

Watch me play at LoR Masters Europe

.02

Research

Research Themes:

• Explainable Physiological Signal Understanding
• Evidence-Grounded Clinical Reasoning & Evaluation
• Ubiquitous Health & Ambient Sensing

Explainable Physiological Signal Understanding

Instruction-tuned LLMs that read raw ECG, PPG, BCG and BSG waveforms, locate diagnostic landmarks, and leave an auditable evidence trail.

NeurIPS 2026 DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition

Jiahui Li, Ruili Fang, Zishuai Liu, Wenzhan Song, Jin Lu, Fei Dou†

[pdf]

ACM IMWUT (UbiComp) 2026 Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Signal

Jiahui Li, Yida Zhang, Zixuan Zeng, Jiayu Chen, Yingjian Song, Yin Xiao, Nishan Dong, Junjie Lu, Younghoon Kwon, Xiang Zhang, Jin Lu, Wenzhan Song, Fei Dou†

[paper] [arXiv]

TS4H Workshop @ NeurIPS 2025 Peak-R1: Instruction-Tuned Large Language Models for Robust J-Peak Detection

Jiahui Li, Yida Zhang, Zixuan Zeng, Jiayu Chen, Xiang Zhang, Jin Lu, Wenzhan Song, Fei Dou†

[openreview]

1 / 3

Evidence-Grounded Clinical Reasoning & Evaluation

Benchmarks and methods that test whether a model's diagnosis is actually supported by retrievable clinical evidence.

Preprint 2026 EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses

Jiahui Li, Ruili Fang, Zishuai Liu, Yutong Guo, Nan Yang, Wenzhan Song, Jin Lu, Fei Dou†

[pdf]

Preprint 2024 GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models

Zicheng Liu, Jiahui Li, Siyuan Li, Zelin Zang, Cheng Tan, Yufei Huang, Yajing Bai, Stan Z. Li

[pdf]

Preprint 2025 Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges

Haoran Lu, Luyang Fang, Ruidong Zhang, and others, including Jiahui Li

[pdf]

1 / 3

Ubiquitous Health & Ambient Sensing

Contactless and smart-home sensing for health monitoring and human activity modeling.

ACM SenSys 2026 ADLGen: Synthesizing Symbolic, Event-Triggered Sensor Sequences for Smart-Home Human Activity Modeling

Weihang You∗, Hanqi Jiang∗, Jiahui Li∗ (co-first author), Zishuai Liu∗, Tianming Liu, Jin Lu, Fei Dou†

[paper]

Preprint 2026 Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography

Yuanyuan Zhang, Yida Zhang, Jiahui Li, Yuyan Wu, Fei Dou, Xiao Yin, Zhenlin An, Hae Young Noh, Wenzhan Song

[pdf]

1 / 2

∗ equal contribution, † corresponding author.

.03

Experience

Education

• 2024 – now
  University of Georgia
  Ph.D. in Computer Science · GPA 4.00/4.00
  Advisor: Dr. Fei Dou
• 2021 – 2022
  University College London
  M.Sc. in Scientific and Data-Intensive Computing
• 2017 – 2021
  University of Liverpool
  B.Sc. in Computer Science and Engineering

Research Experience

• 2024 – now
  Graduate Research Assistant, School of Computing, University of Georgia
  Advisor: Dr. Fei Dou
• 2023 – 2024
  Research Assistant, Hong Kong University of Science and Technology
  Supervisor: Prof. Dit-Yan Yeung. Built MGTST, a multi-scale, cross-channel gated Transformer for multivariate long-term forecasting.

Teaching

• Fall 2025, Fall 2026
  Teaching Assistant, CSCI 4470: Algorithms, UGA
• Fall 2024, Spring 2025
  Teaching Assistant, CSCI 1302: Software Development, UGA