Shiguang Wu is a M.Sc. student and research-focused intern with nine years of software experience, currently working on generative retrieval models (differentiable search indices) at WeChat’s 视频号 in the Netherlands. He studies and implements neural retrieval systems with a particular interest in their mechanistic and theoretical underpinnings, bridging hands-on model development and formal analysis. Trained at Shandong University in computer science, he brings both academic rigor and practical engineering discipline to retrieval research. Notably, he combines experience across industry and research settings, positioning him to translate theoretical insights about neural retrieval into scalable, production-ready retrieval features.
9 years of coding experience
Master's degree, Computer Science, Master's degree, Computer Science at Shandong University
This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.
Contributions:29 PRs, 47 pushes, 29 branches in 2 years 2 months
Contributions:5 commits, 180 pushes, 8 branches in 27 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.