Pengfei Hu

Department of Computer Science, Stevens Institute of Technology

prof_pic.jpg

Gateway South 433

1 Castle Point Terrace, Hoboken, NJ 07030

My name is Pengfei Hu. I’m a 3rd year Ph.D. student in Department of Computer Science at Stevens Institute of Technology, advised by Prof. Yue Ning. Before that, I obtained my master’s degree from the Viterbi School of Engineering, University of Southern California in 2023, where I worked with Prof. Sze-chuan Suen.

My current research concentrates on predictive healthcare on electronic health records (EHR), with a specific focus on augmented (e.g. knowledge-guided and retrieval augmented) language models and their robustness (e.g. generalization and transparent adaptation) under domain shifts. I have also worked on graph neural networks and multi-agent design.

Feel free to drop me an email (phu9 at stevens dot edu) if you have any questions about my research, or want to discuss about potential collaborations.

I am looking for internship industrial opportunities, starting from Summer 2026. Feel free to reach out if there is a good fit!

Educations

Stevens Institute of Technology (2023 - Present)
Ph.D. in Computer Science
GPA: 3.95/4.00
Research Focus: EHR modeling, Clinical NLP, Large Language Models.
Advisor: Prof. Yue Ning

University of Southern California (2021 - 2023)
M.S. in Industrial System Engineering
GPA: 4.00/4.00
Research Focus: Anomaly Detection by Wearable Sensor Devices.
Advisor: Prof. Sze-chuan Suen

Industrial Experience

Oak Ridge National Laboratory (May 2025- Aug. 2025)
Graduate Research Intern, Computational Sciences and Engineering Division
Topic: Reservoir Inflow Forecasting. [Two Workshop and One Journal papers]
Mentor: Fan Ming

Alibaba Group (Mar. 2021 - Jul 2021)
Data Analyst Intern, Cainiao Network
Mentor: Hao Lin

Tencent (Apr. 2020 - Aug. 2020)
Product Analyst Intern, Tencent Music Entertainment Group (TME)
Mentor: Hongmin Liao

PricewaterhouseCoopers (Jan. 2019 - Mar. 2019)
Actuarial Assurance Intern
Manager: Congyan Liu


News

Feb 27, 2026 Our paper AGFormer: Adaptive Spatiotemporal graph informed transformer for multi-reservoir inflow forecasting is accepted to Environmental Modelling & Software (IF: 4.6).
Feb 22, 2026 Our paper Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning is accepted to IEEE Journal of Biomedical And Health Informatics (IF: 6.7).
Nov 17, 2025 My intern paper AdaTrip and HydroDCM are accepted by the ICDM 2025 DMESS and the AAAI 2026 AI4ES (Oral) workshops.
Aug 20, 2025 Our paper II-KEA is accepted by EMNLP 2025 Findings!
May 19, 2025 I will be joining the Oak Ridge National Lab as a summer graduate research intern.
Oct 10, 2024 I passed my oral qualification exam.
May 15, 2024 I passed my written qualification exam.

Selected Publications

  1. arXiv
    Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference
    Pengfei Hu, Chang Lu, Feifan Liu, and 1 more author
    arXiv preprint arXiv:2602.12542, 2026
    HTML
  2. arXiv
    UdonCare: Hierarchy Pruning for Unseen Domain Discovery in Predictive Healthcare
    Pengfei Hu, Xiaoxue Han, Fei Wang, and 1 more author
    arXiv preprint arXiv:2506.06977, 2025
    HTML
  3. IEEE JBHI
    Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
    Pengfei Hu, Chang Lu, Fei Wang, and 1 more author
    IEEE Journal of Biomedical and Health Informatics, 2026
    HTML PDF
  4. Elsevier EMS
    AGFormer: Adaptive Spatiotemporal graph informed transformer for multi-reservoir inflow forecasting
    Ming Fan, Pengfei Hu, Xiaoxue Han, and 4 more authors
    Environmental Modelling & Software, 2026
    HTML PDF
  5. EMNLP 2025 Findings
    No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery
    Xiaoxue Han, Pengfei Hu, Jun-En Ding, and 3 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
    HTML