Hi! I am a 4th-year CSE Ph.D. student at the University of Washington, advised by Su-In Lee at Artificial Intelligence for Biological and Medical Sciences (AIMS). My research focuses on the intersection of explainable AI, particularly feature and data attribution, generative models, and treatment effect estimation. I apply these methods to improve model transparency, fairness, and safety, aiming to enhance understanding and decision-making in complex real-world settings, particularly in the biomedical domain.
I’ve been fortunate to work with many amazing people, and I’m always excited about new opportunities to collaborate. You can reach out to me at mingyulu[at]cs[dot]washington[dot]edu
I will be working with Suraj Srinivas and Jorge Piazentin Ono at Bosch Research during the summer of 2025!
Chris Lin *, Mingyu Lu * , Su-In Lee. An Efficient Framework for Crediting Data Contributors of Diffusion Models ICLR 2025 [paper] [project page][code]
Ian Connick Covert, Wei Qiu, MingYu Lu, Na Yoon Kim, Nathan J White, Su-In Lee. Learning to maximize mutual information for dynamic feature selection ICML 2023 [paper] [code]
Mahtab Bigverdi, Wisdom Oluchi Ikezogwo, Kevin Minghan Zhang, Hyewon Jeong, MingYu Lu, Sungjae Cho, Linda Shapiro, Ranjay Krishna ``MedBLINK:Probing Visual Perception and Trustworthiness in Multimodal Language Models for Medicine’’ Computer Vision for Automated Medical Diagnosis (CVAMD) at ICCV 2025 (Oral) [paper][datasets & project page]
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park``BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum’’ EMNLP 2025 [paper] [project page]
Yubin Kim, Hyewon Jeong, Chanwoo Park, MingYu Lu, Eugene W Park, Haipeng Zhang, Xin Liu, Hyeonhoon Lee, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park ``Tiered Agentic Oversight: A Hierarchical Multi-Agent System for AI Safety in Healthcare’’ Multi-Agent Systems (MAS) in the Era of Foundation Models at ICML 2025 [paper]
Yubin Kim, Hyewon Jeong, Shan Chen, Shuyue Stella Li, Mingyu Lu, Kumail Alhamoud, Jimin Mun, Cristina Grau, Minseok Jung, Rodrigo Gameiro, Lizhou Fan, Eugene Park,Tristan Lin, Joonsik Yoon, Wonjin Yoon, Maarten Sap, Yulia Tsvetkov, Paul Liang, Xuhai Xu, Xin Liu, Daniel McDuff,Hyeonhoon Lee, Hae Won Park, Samir Tulebaev, Cynthia Breazea “Medical Hallucination in Foundation Models and Their Impact on Healthcare” MedRxiv 2025 [paper]
Mingyu Lu, Ethan Weinberger, Chanwoo Kim, Su-In Lee CellCLIP – Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning. Learning Meaningful Representation for Life (LMRL) Workshop at ICLR 2025 (Oral) [paper] [code]
Mingyu Lu, Ian Covert, Nathan J White, Su-In Lee. CODE-XAI: Construing and Deciphering Treatment Effects via Explainable AI using Real-world Data. medRxiv 2024 [paper]
MingYu Lu, Yifang Chen, Su-In Lee. A Deep Bayesian Bandits Approach for Anticancer Drug Screening: Exploration via Functional Prior. Adaptive Experimental Design and Active Learning in the Real World Workshop at ICML 2022 [paper]
Rui Li, Stephanie Hu, Yuria Utsumi, MingYu Lu, Prithwish Chakraborty, Daby Sow, Piyush Madan, Jun Li, Mohamed Ghalwash, Zachary Shahn, Li-wei H Lehman. G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes. Machine Learning for Health (ML4H) Workshop at NeurIPS 2021.[paper]
MingYu Lu, Zach Shah, Finale Doshi Velez, Li-Wei Lehman. Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Sepsis Treatment. American Medical Informatics Association (AMIA) 2020 Distinguished Paper. [paper]
Year | Leadership/Awards |
---|---|
2020 | Organizer of NewInML at NeurIPS 2020 |
2019 | LEAP Fellowship of the Ministry of Science and Technology of Taiwan. |
2017 | CoFounder of TinyNote |