Kai Yi

About Kai Yi

I am currently a Research Scientist at Meta in Sunnyvale, working on model compression and inference acceleration. I received my PhD in Computer Science under the guidance of Prof. Peter Richtárik in June 2025. Prior to that, I completed my Master’s degree under the supervision of Prof. Mohamed Elhoseiny at KAUST in December 2021. I earned my Bachelor of Engineering with honors from Xi’an Jiaotong University (XJTU) in June 2019.I have had the opportunity to intern at several leading research institutions, including Sony AI, Vector Institute, Tencent AI Lab, CMU Xulab, NUS CVML Group, and SenseTime Research.My primary research interest lies in centralized and federated LLM compression. My work is highly interconnected, featuring notable contributions such as the LLM post-training compression algorithms SymWanda and PV-Tuning (NeurIPS Oral), with more in progress; communication-efficient federated learning methods CohortSqueeze (NeurIPS-W Oral), FedP3 (ICLR), and EF-BV (NeurIPS); and multimodal language model projects DACZSL (ICCVW), HGR-Net (ECCV), and VisualGPT (CVPR).

Experience

1. Research Scientist

   Meta

   Aug 2025 — Present · Sunnyvale, CA, US

   Model compression and inference acceleration.

Education

• KAUST (King Abdullah University of Science and Technology)

  MS of Computer Science, Computer Vision and Machine Learning

• KAUST (King Abdullah University of Science and Technology)

  PhD Candidate of Computer Science, Machine Learning Optimization

• Xi'an Jiaotong University

  Bachelor's degree, Computer Software Engineering

  2015 — 2019