Le Peng

Email: peng0347 [at] umn [dot] edu

I am a senior research scientist at Meta. Previously, I received my Ph.D in Computer Science at University of Minnesota (UMN) advised by Prof. Ju Sun and I completed B.Sc. in Computer Science and Engineering at Harbin Institute of Technology (HIT). I am interested in machine learning, deep learning, computer vision, natural language processing, and AI+X.

🌟 News 🌟

[Feb 2026] I am starting a full-time role at Meta as a Senior Research Scientist.
[Jun 2025] Check out recent released paper " Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classification " on how to leverage constrained optimization to enhance learning from imbalanced data with rigous metric constraints.
[Jun 2025] I have defended his thesis titled Towards Robust and Reliable Artificial Intelligence in Healthcare.
[Sep 2024] I will be joining Meta as a research scientist.
[May 2024] Check out recent released paper " Selective Classification Under Distribution Shifts " on enhancing AI model safety under real-world distribution shifts using selective classification.
[Apr 2024] Our paper "Federated Learning with Convex Global and Local Constraints" is accepted by TMLR.
[Mar 2024] Our paper " An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing for Information Extraction" is accepted by npj Digital Medicine (IF: 15.2).
[Oct 2023] Our paper "Federated Learning with Convex Global and Local Constraints" is available on Arxiv, which will also be served as a poster presentation at NeurIPS'23 workshop on Optimization for Machine Learning
[Aug 2023] Our paper "Rethinking Transfer Learning in Medical Imaging"" is accepted by British Machine Vision Conference (BMVC'23) (oral)
[Aug 2023] I will give a poster presentation at KDD'23 workshop on Federated Learning for Distributed Data Mining.
[Jul 2023] Our paper " A Systematic Evaluation of Federated Learning on Biomedical Natural Language Processing" is available on ArXiv.
[Jun 2023] I will present our work on imbalanced learning at EBAIC@ICHI'23. The work formulates imbalanced problems into constrained optimization problems which give better feasibility compared with SOTA methods.
[May 2023] I am glad to present my research in transfer learning, imbalanced learning, and federated learning in MMLS'23.
[Mar 2023] I will start a new role as a research intern at Truveta this summer.
[Feb 2023] I am honored to be recognized as Cisco Research Graduate Awardee
[Oct 2022] Our short paper "Imbalanced Classification in Medical Imaging via Regrouping." is accepted by NeurIPS’22 Workshop: When Medical Imaging Meets NeurIPS!
[Oct 2022] My poster won the 3rd prize at 2022 IEM Annual Conference Poster Competition!
[Sep 2022] I will have a poster presentation at 2022 IEM annual conference!
[Sep 2022] Our paper "Evaluation of Federated Learning Variations for COVID-19 diagnosis using Chest Radiographs from 42 US and European hospitals." is accepted by Journal of the American Medical Informatics Association (JAMIA)! (IF: 7.9)
[May 2022] Our paper "A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals" has been accepted by Radiology: Artificial Intelligence!
[Nov 2021] I am honored to be recognized as Cisco Research Fellow!
[Oct 2021] Our paper “Early Stopping for Single-Instance Deep Generative Priors. ” is accepted by British Machine Vision Conference (BMVC) 2021!
[Sep 2021] Our federated learning research project is highlighted in NVIDIA Clara white paper!
[Sep 2021] We are the among first group that builds a real-world federated learning system in healthcare. Thanks to our collaborators from Health Fairview, Emory University, Indiana University, and NVIDIA!
[Aug 2021] Our paper "A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals" is submitted to Radiology: Artificial Intelligence! (IF: 9.8)
[Jun 2021] Our paper "Rethink Transfer Learning in Medical Imaging" is now live on arxiv!
[Sep 2020] Our COVID-19 healthcare project is highlighted in CSE News, UMN News, and StarTribune!
[Sep 2020] We developed a COVID-19 diagnosis system and deployed it to 12 U.S. Hospitals!
[Aug 2020] I will have a poster presentation at Fall Bioinformatics and Computational Biology (BICB) Symposium.

Total visits to this site: