Who Are We?

Welcome to the Optimization for Artificial Intelligence (OptimAI) Lab in the Department of Electrical and Computer Engineering at the University of Minnesota. Our goal is to develop principled optimization algorithms that advance artificial intelligence, information/signal processing and machine learning systems, bridging the gap between theoretical foundations and practical applications.

Our research focuses on:

Theoretical Foundations: First-order and zeroth-order stochastic algorithms, momentum-based methods, bi-level optimization, min-max optimization, and equilibrium analysis for noncooperative games.
LLM & Diffusion Applications: LLM agents, alignment for large language models and diffusion models, parameter-efficient fine-tuning, and scalable training algorithms.
Robust & Private ML: Robust machine learning, inverse reinforcement learning, differential privacy, and federated learning.

Open Positions

We have research assistant and postdoctoral fellow positions available in the general areas of optimization, diffusion models, and LLM. If you are interested, please contact Dr. Hong.

News

May 22, 2026	A new paper On the Nature of Regularity Assumptions in Bilevel Optimization with Constrained Lower-level Problem, joint work with Xiaotian, Chuan and Shuzhong is available here. In this work, we study the regularity assumptions underlying bilevel optimization when the lower-level problem is constrained.
May 20, 2026	Welcome Dawei Li to the group as a post-doctoral researcher!
May 15, 2026	M. gave a talk at the Department of Industrial Engineering and Management Sciences (IEMS) at Northwestern University, titled “When Classical Optimization Meets Modern Foundation Models: New Algorithms, Theory, and Insights”. The slides can be found here. This talk included a few of our new results, including an interpretation of SGD, and making Nesterov’s lookahead momentum work as a “harness” to accelerate pretraining algorithms (see here).
May 01, 2026	Five papers accepted by ICML 2026. Congratulations to everyone! “Hiper: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents”, J. Peng, Y. Liu, R. Zhou, C. Fleming, Z. Wang, A. Garcia, M. Hong. See here “A Minimalist Optimizer Design for LLM Pretraining”, A. Glentis, J. Li, A. Han, M. Hong. See here “StitchCUDA: An Automated Multi-Agent End-to-End GPU Programming Framework with Rubric-based Agentic Reinforcement Learning”, S. Li, Z. Zhang, W. Chen, Y. Luo, M. Hong, C. Ding. See here “Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding”, H. Reisizadeh, J. Ruan, Y. Chen, S. Pal, S. Liu, M. Hong. See here “GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding”, B. Lei, N. Xu, A. Payani, M. Hong, C. Liao, Y. Cao, C. Ding. See here
Mar 15, 2026	Our paper BLUR: A Bi-Level Optimization Approach for LLM Unlearning has been accepted to EACL 2026 (Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, Volume 1: Long Papers). Joint work with Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Sijia Liu, and Mingyi Hong. Code available here.
Mar 01, 2026	Together with Dr. Jiaxiang Li, M. organized three sessions at the INFORMS Optimization Society Annual Meeting (March 2026): two on optimizer design and benchmarking for LLM pretraining, and one on bilevel optimization. Session 1: Meisam Razaviyayn (USC), Weijie Su (Wharton, University of Pennsylvania), Aaron Defazio (Meta), Athanasios Glentis (University of Minnesota). Session 2: Kaan Ozkara (Amazon), Kaiyue Wen (Stanford University), Hao-Jun Michael Shi (Meta), Maria-Eleni Sfyraki (UC San Diego), Tuo Zhao (Georgia Tech). Session 3 (Bilevel Optimization): Yuchen Lou (Northwestern University), Sanyou Mei (HKUST), Xiaotian Jiang (University of Minnesota), Jie Wang (CUHK-Shenzhen).
Feb 01, 2026	Our tutorial paper Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design, joint work with Siliang, Luca, Chenliang, Jiaxiang, Volkan (EPFL), Stephano (Stanford), Markus (Google) and Alfredo (TAMU), has been accepted by SPM.
Jan 01, 2026	Mingyi and Jiaxiang are organizing three sessions on INFORMS Optimization Society Conference (IOS). Two sessions on optimization for foundations models, and one on bilevel optimization.
Dec 01, 2025	M. is awarded a JPMorgan Chase Faculty Research Award to support the research on the general direction of optimization for foundation models.
Nov 10, 2025	Dawei Li joined the group as a visiting researcher. Dawei obtained PhD degree from the Department of Industrial and Enterprise Systems Engineering from UIUC. Welcome!
Nov 05, 2025	Chung Yiu (Oscar) Yau joined the group as a Post-Doctoral Fellow. Oscar obtained PhD degree from the Department of Systems Engineering and Engineering Management from Chinese University of Hong Kong. Welcome!
Nov 01, 2025	A new set of tutorial slides on bilevel optimization developed by M. and Prof. Steve Wright can be found here.
Sep 15, 2025	M. Receives the Egon Balas Prize from INFORMS Optimization Society. This prize is awarded annually to an individual for a body of contributions in the area of optimization. See here for the CSE announcement.
Sep 10, 2025	A new paper A Correspondence-Driven Approach for Bilevel Decision-making with Nonconvex Lower-Level Problems, joint work with Xiaotian, Jiaxiang and Shuzhong is available here. In this work, we study challenging bilevel optimization problems where the lower-level problem is non-convex.
Sep 05, 2025	Welcome Zijian Zhang (ECE) and Shuyu Gan (CSE, co-advised with DK) who joined the group as first-year PhD students.
Jul 10, 2025	A new 3-year grant Collaborative Research: Unregistered Spectral Image Fusion in Remote Sensing: Foundations and Algorithms is awarded by NSF (joint work with Xiao). In this work, we develop theory and algorithms for challenging fusion tasks in remote sensing.