About me

I’m an incoming Ph.D. student at the National University of Singapore (NUS), where I will be advised by Prof. Mengling Feng. I recently completed my Master’s degree at School of Software Engineering, Xi’an Jiaotong University. I am very fortunate to be advised by Prof. Zhao of Smiles Lab from School of Computer Science, Xi’an Jiaotong University. I was the visiting student working with Dr. Li-wei H. Lehman and Prof. Roger Mark in Institute for Medical Engineering & Science (IMES), MIT. My research interest includes Time series, Generative Modeling, Machine Learning, representation learning, Self-supervised learning and AI for Healthcare.

You can find my CV here: Feng’s CV

In my spare time, I like to spend time in the swimming pool. My current goals are to swim 1000 meters breaststroke within 24 minutes and to swim continuously for 1000 meters freestyle.

Email: wufeng@stu.xjtu.edu.cn / wufeng@mit.edu / Gamil: meiyoufeng116@gmail.com / Github

Research interest

1. Time Series Modeling. Mining features from multivariate time series (Self-supervised learning) and using deep learning methods (RNN, Transformer, Diffusion) for prediction of subsequent series.
2. Treatment Effect Prediction. Use causal inference models/counterfactual prediction methods to predict patient outcomes under different treatment plans.
3. Uncertainty Quantification on Treatment Effect. Develop robust deep learning models for healthcare issues, informing clinicals of the credibility of the model.
4. Diffusion Model on Clinical Sequence. Generate treatment/outcome trajectories under different scenarios using the diffusion model and provide decision-making support.
5. Foundation Model on Healthcare. Integrating EHR data to establish Foundation Models from a multimodal perspective including text and images.

Publications

Gem: Empowering mllm for grounded ecg understanding with time series and images.

Xiang Lan, Feng Wu, Kai He, Qinghao Zhao, Shenda Hong, Mengling Feng

ArXiv 2025

Uncertainty Quantification for Conditional Treatment Effect Estimation under Dynamic Treatment Regimes

Leon Deng, Hong Xiong, Feng Wu, Sanyam Kapoor, Soumya Ghosh, Zach Shahn, Li-wei H. Lehman.

Machine Learning for Health 2024 Symposium (ML4H 2024)

Self-Supervised State Space Modeling for Clinical Time Series with Long-Range Dependency.

Feng Wu, Sanyam Kapoor, Guoshuai Zhao, Rahul Krishnan, Gari Clifford, Roger Mark, Li-wei H. Lehman.

Alleviating User-Sensitive bias with Fair Generative Sequential Recommendation Model.

Yang Liu, Feng Wu.

International Conference On Intelligent Computing (ICIC 2025).

Submitting

G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes.

Hong Xiong, Feng Wu, Leon Deng, Megan Su, Li-wei H Lehman.

Machine Learning for Healthcare (MLHC). 2024.

Improving Conversation Recommendation System Through Personalized Preference Modeling and Knowledge Graph.

Feng Wu, Guoshuai Zhao, Tengjiao Li, Jialie Shen, Xueming Qian.

IEEE Transactions on Knowledge and Data Engineering. 2024

Forecasting Treatment and Response Over Time Using Alternating Sequential Models.

Feng Wu, Guoshuai Zhao, Yuerong Zhou, Li-wei H Lehman.

IEEE Trans on Biomedical Engineering. 2023.

A Large Scale Annotated Dataset of Ventricular Tachycardia Alarms from ICU Monitors.

Li-wei H. Lehman, Benjamin E Moody, Harsh Deep, Feng Wu, Hasan Saeed, Lucas McCullum, Diane Perry, Tristan Struja, Qiao Li, Gari Clifford, Roger Mark.

Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (NIPS 2023)

A Diffusion Model with Contrastive Learning for ICU False Arrhythmia Alarm Reduction

Feng Wu, Guoshuai Zhao, Xueming Qian, Li-wei H. Lehman

IJCAI 2023