University of Arizona, Huanrui Yang 교수님의 세미나가 7월 10일에 진행될 예정입니다.

관심 있는 학생 여러분들의 많은 참석 바랍니다.

■일시: 2026. 7. 10 (금요일) 13:30 ~ 15:00

■장소: 반도체관 400112호

■주제: “From Static to Dynamic: A Journey of Accurate and Flexible Low-Precision Quantization”

■연사: Huanrui Yang 교수님 (University of Arizona)

Huanrui Yang is an Assistant Professor in the Department of Electrical and Computer Engineering (ECE) at the University of Arizona (UA). Before joining the UA in 2024, he was a Postdoctoral Scholar in the EECS department of UC Berkeley and Berkeley AI Research. He obtained Ph.D. in ECE from Duke University in 2022 and B.E. in Electronic Engineering from Tsinghua University in 2017. He is featured in WAIC 2021 Future Star Award and AAAI 2026 New Faculty Highlights. His primary research focuses on the efficiency and robustness of deep neural network models, where he aims to identify the core functionality of the deep learning model and develop the most efficient and robust algorithm to fulfill such functionality. Applications of his research spans across computer vision, generative model, and natural language processing.

■ABSTRACT

Quantization has been the key of the efficient deployment of large AI models. In this talk, I will discuss my recent work in the field of foundation model quantization. I will cover the full spectrum of highly accurate post-training quantization technique for foundation models, effective mixed-precision quantization scheme search for mixture-of-experts, and dynamically changing the quantization precision on the fly to fit hardware resource constraints. I will end my talk with a vision on the application of quantization, together with other efficiency techniques, in the era of agentic inference of foundation models.

■HOST: 고종환교수 (전자전기컴퓨터공학과)