ÂÜÀòÂÒÂ×

Yunqiang Li is a Deep Learning Research Engineer at Axelera AI since April 2022, specializing in network pruning, neural architecture search, efficient fine-tuning of large language models, and quantization. Li has developed a pruning toolkit that supports various models, including CNNs, Transformers, YOLO, and LLMs, enabling dynamic and one-shot pruning algorithms. Since February 2018, Yunqiang Li has also served as a Guest Researcher at Technische Universiteit Delft, contributing to research on pruning and single bit quantization, resulting in publications at ICCV2023 and ICLR2023. Previously, as a PhD student at Delft University of Technology, Li focused on deep compression, producing four first-author papers at top-tier conferences while obtaining a Doctor of Philosophy in Computer Science.