Events Calendar

ECE Seminar: Mingyi Hong

Title: Old and New Optimization Techniques for Foundation Model Fine-Tuning and Pre-Training

Abstract: As large language models (LLMs), such as ChatGPT and DeepSeek R1, have taken the world by storm, it is clear that generative AI systems will soon become ubiquitous in our lives. However, these systems, particularly the foundational models they are based on, face significant challenges, such as potential privacy breaches and difficulties in reliably learning and aligning with human preferences. This talk will explore recent advancements in pretraining and fine-tuning foundational models, such as LLMs and vision models, to enhance their performance across various dimensions. First, we will introduce an approach that employs inverse reinforcement learning and bi-level optimization to align large language models (LLMs) with human feedback. Additionally, we will examine the application of other classical techniques from signal processing and optimization for efficient and privacy-preserving training of LLMs. The overarching goal of this talk is to demonstrate the critical role of sophisticated optimization modeling and algorithm design in advancing the capabilities of AI systems.

Bio: Mingyi Hong received his Ph.D. degree from the University of Virginia, Charlottesville, in 2011. He is currently an Associate professor in the Department of Electrical and Computer Engineering at the University of Minnesota, Minneapolis. His research has been focused on developing optimization theory and algorithms for applications in signal processing, machine learning and foundation models. He is a Senior Area Editor for IEEE Transactions on Signal Processing. His work has received two IEEE SPS Best Paper Awards (2021, 2022), an International Consortium of Chinese Mathematicians Best Paper Award (2020), and a few Best Student Paper Awards in signal processing and machine learning conferences. He is an Amazon Scholar, and he is the recipient of an IBM Faculty Award, Meta research awards, Cisco Research Awards, and the 2022 Pierre-Simon Laplace Early Career Technical Achievement Award from IEEE SPS.