Rulin Shao

I am a second-year PhD at University of Washington advised by Prof. Pang Wei Koh and Prof. Luke Zettlemoyer . I am also a visiting researcher at Meta working with Scott Yih and Mike Lewis . I completed my master's in Machine Learning at CMU advised by Prof. Eric Xing and my undergraduate degree in Mathematics at XJTU.

I'm interested in building an AI system that can automatically collect information from diverse sources, conduct deliberate practice, and decide how to spend time, compute, and storage to handle complex tasks.

Google Scholar  /  GitHub  /  Twitter  /  LinkedIn  /  Email

• 2025-05 Introducing Spurious Rewards: Rethinking Training Signals in RLVR . We showed Qwen models can work even with random rewards! 🤯
• 2025-04 Introducing ReasonIR , a retriever specifically trained for reasoning tasks. Code, data, and model are released!
• 2024-11 Check out our OpenScholar , an AI assistant proficient at answering research questions with accurate paper citations using online paper resources! Try out our demo!
• 2024-07 Introducing MassiveDS-1.4T , the first open-source trillion-token datastore and datastore scaling study! We release codes for distributed indexing and API serving make datastore scaling study accessible. [code]
• 2023-10 Introducing DistFlashAtten , a distributed memory-efficient attention with sequence parallelism for Long-context LLMs training!

My boyfriend asked me to put him here :). He is awesome!