Ying Sheng(盛颖)
I got my Ph.D. in Computer Science at Stanford University (Centaur), where I was very fortunate to be advised by Clark Barrett. Before that, I received an M.S. in Computer Science from Columbia University in 2017 and a B.E. in Computer Science and Technology from ACM Honored Class, Shanghai Jiao Tong University in 2016.
I was a visiting researcher at Sky@UC Berkeley, working with Ion Stoica and Joseph E. Gonzalez (2023-2024); a Ph.D. resident at X, the moonshot Factory (the team graduated to Labs@Google during my residence) (2022), working on AI for Code with Michele Catasta; a research intern at Facebook Novi (2021), working on smart contract verification with Prof. David Dill; a quantitative software engineer at Two Sigma (2018); and a research intern at Microsoft Research Asia (2015), working with Chin-Yew Lin.
NEWS:
The fastest way to find me is through SGL Slack. At the SGLang open-source project, we are looking for open-source enthusiasts and learners to help with project and community building. Please contact us through SGL Slack, GitHub, or email.
I will be joining UCLA's Computer Science department as an assistant professor in Fall 2026. Before then, I am looking for 1-2 prospective students who like coding and are passionate about topics in AI, reasoning, and systems. We will aim to make steady progress with small milestones along the way, but the ultimate goal of our research is to create something impactful and real, which is expected to be either novel or practical. People with strong research backgrounds or rich industry experience (open-source projects and internships are included) are preferred.
Follow our blog posts at LMSYS Org. We are founding LMSYS as a non-profit corporation to incubate early-stage open-source projects. Stay tuned for more information.
Contact: [email protected]
Github: https://github.com/Ying1123
Research Interests:
Large Language Models, Machine Learning Systems, Machine Learning for Programs.
Formal Methods, Automated Reasoning.
Code Generation.
I like collaboration and competition. :)
Projects:
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable.
S-LoRA is a lightweight system for serving thousands of LoRA adapters concurrently.
cvc5 is an open-source automatic theorem prover for Satisfiability Modulo Theories (SMT) problems.
FlexGen is a high-throughput generation engine for running large language models with limited GPU memory.
FastChat is an open platform for training, serving, and evaluating large language model based chatbots.
Vicuna is a chatbot trained by fine-tuning LLaMA on user-shared conversations.
Selected Awards
Machine Learning and Systems Rising Stars (ML Commons) 2023.
Human-Centered Artificial Intelligence (HAI) Graduate Fellowship Program, Stanford University 2022 - 2023.
Best tool paper award at the 28th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS), Springer, 2022.
Best paper award at International Joint Conference on Automated Reasoning (IJCAR) 2020.
School of Engineering Fellowship, Stanford University 2018 - 2019.
ACM International Collegiate Programming Contest(ICPC) World Finalist 2018.
Champion in ACM International Collegiate Programming Contest (ICPC) Greater New York 2017.
Course Assistant Fellowship (<2%), Columbia University 2017.
Silver Medal in National Olympiad in Informatics (NOI) 2011, China.
Teaching
Teaching Assistant at Stanford University(2021): The Modern Algorithmic Toolbox (Spring).
Teaching Assistant at Stanford University(2020): Formal Methods for Computer Systems (Fall).
Teaching Assistant at Columbia University(2017): Algorithm Analysis I (Spring, Fall), Introduction to Computational Complexity(Summer).
Teaching Assistant at Shanghai Jiao Tong University(2015): Set Theory and Mathematical Logic (Spring).
ACM/ICPC Team Coach at Shanghai Jiao Tong University(2014 - 2015): The team won a Bronze medal (9th Place) in ACM/ICPC World Final 2015