Profiles

Kai Yi is a PhD candidate in Computer Science at King Abdullah University of Science and Technology (KAUST), supervised by Peter Richtarik and working in the Optimization and Machine Learning Lab. He earned his master’s degree in Computer Science at KAUST in 2021 under the supervision of Mohamed Elhoseiny. He completed his Bachelor of Engineering with honors at Xi’an Jiaotong University (XJTU) in 2019.

He has interned at several leading research institutions, including Sony AI, Vector Institute, Tencent AI Lab, CMU Xulab, NUS CVML Group, and SenseTime Research. His primary research focuses on centralized and federated LLM compression. His work is highly interconnected, featuring significant contributions such as the LLM post-training compression algorithms SymWanda and PV-Tuning (NeurIPS Oral); communication-efficient federated learning methods Cohort-Squeeze (NeurIPS-W Oral), FedP3 (ICLR), and EF-BV (NeurIPS); and multimodal language model projects DACZSL (ICCVW), HGR-Net (ECCV), and VisualGPT (CVPR).

He actively serves as a reviewer for leading journals, including TPAMI, IJCV, and TMC, as well as top conferences such as NeurIPS, ICLR, ICML, CVPR, ECCV, and ICCV.

Kai Yi's primary research interest lies in centralized and federated LLM compression. My work is highly interconnected, featuring significant projects such as the LLM post-training compression algorithms SymWanda and PV-Tuning (NeurIPS Oral), with more on the way; 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). His research interests include:

• Machine learning optimization in the large-scale data/model era.
• Conceptual-level knowledge transfer learning: theories and applications.

Specifically, he works on machine learning optimization, federated learning, and zero-shot learning. He is particularly interested in accelerated local training methods and personalized federated learning in data and system heterogeneity.