Summary
Siyuan Li is a PhD candidate at ETH Zürich's Computer Vision Lab with nine years of experience building cutting-edge perception systems and generative models. He focuses on open-world object tracking under the supervision of Dr. Martin Danelljan and Prof. Luc Van Gool, blending rigorous academic research with practical system-building. His industry experience includes internships at Meta SuperIntelligence Lab, Disney Research, and Tencent AI Lab, where he worked on multimodal foundation models, real-time human matting, and image generation. Based in Shanghai and Switzerland, Siyuan combines a strong academic lineage from ETH, EPFL, and Wuhan University with hands-on engineering fluency (as his GitHub quip, "Talk is cheap, import tensorflow as tf," suggests). He is equally comfortable prototyping research code and integrating models into real-time pipelines, often prioritizing deployable solutions over purely theoretical results. Colleagues describe him as a researcher who consistently bridges state-of-the-art ideas and production-ready implementations.
9 years of coding experience
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Wuhan University
Master of Science - MS Computer Science, Master of Science - MS Computer Science at EPFL
PhD student Computer Vision Lab @ ETHZ, PhD student Computer Vision Lab @ ETHZ at ETH Zürich