Jiayi Yuan

About me

I’m Jiayi Yuan ([dʒa-ˈi:], 袁加熠), a Ph.D. student from the Department of Computer Science at Rice University, advised by Dr. Xia “Ben” Hu. My research interests include efficient and trustworthy machine learning, and its applications in language, vision, time series and graph data. Recently, I’m focusing on efficiency and safety problems of large language models (LLMs).

Previously, I received my bachelor’s degree in computer science from Tsinghua University, where I also studied statistics as a minor.

I lived in Beijing for 22 years and in Houston for $YEAR-2022 year(s).

Education

• Ph.D. in Computer Science, 2022 - now. Rice University, Houston, TX

• B.Eng. in Computer Science and Technology, 2017 - 2021. Tsinghua University, Beijing, China

Highlights

• KIVI largely inspires KV Cache quantization in Huggingface and is integrated into Transformers. Full code is available here.

• Rice News: Large language models could be the key to better patient-trial matching - Rice CS Ph.D. student wins AMIA Best Student Paper Award.

• Rice News: Rice CS’ Xia Ben Hu investigates LLMs and likely applications.

News

• Checkout our latest survey on efficient LLM reasoning! Feel free to UPVOTE

• Checkout our recent insights and discussions on LLM evaluation

• One paper accepted by NAACL 2025 (Finding). See you in Albuquerque!

• Two papers accepted by EMNLP 2024 (Main + Finding). See you in Miami!

• Checkout our recent benchmarking works on KV Cache compression, time series foundation models and LLM evaluation!

• Two papers accepted by ICML 2024. See you in Vienna!

• Our LLM-PTM paper is selected as a best student paper at AMIA 2023

• One paper accepted by NeurIPS 2023

• Joined Microsoft Accelerating Foundation Models Research program

• Two papers accepted by AMIA 2023

• …

Publications

Please refer to publications or Google Scholar.