My research interests lie in exploring the intersection of reinforcement learning and foundation models. I am deeply passionate about creating innovative algorithms and systems that address diverse decision-making challenges in reasoning and agentic tasks.

Research Fellow, Master of Science in Computer Engineering @ Columbia University | Bachelor of Science in Math-Computer Science @ UC San Diego · 👋 Hi, I’m Yuxiao (Lily) Qu!

Conversation Design of a Smart Display for Older Adults Based on Politeness Theory. Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems …

Aug 24, 2022 · Student - Carnegie Mellon University · I am currently a PhD student at CMU · Experience: Morgridge Institute for Research · Education: Carnegie Mellon University · Location: Pittsburgh · 190...

Can language models be used for real-world urban-delivery route optimization?

Optimizing Test-Time Compute via Meta Reinforcement Finetuning Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar Preprint

Yuxiao Qu PhD student, Machine Learning, Carnegie Mellon University Joined March 2022

2022 Simulation-Acquired Latent Action Spaces for Dynamics Generalization. Nicholas Corrado, Yuxiao Qu, Josiah P. Hanna. Proceedings of the 1st Conference on Lifelong Learning Agents (CoLLAs). August 2022. Abstract

‪Lead Software Engineer, Wells Fargo‬ - ‪‪Cited by 1,002‬‬ - ‪software testing‬ - ‪software engineering‬ - ‪data analytics‬ - ‪data visualization‬

Hong Guang Zhang, Guan Yu Jin, Yu Xiao Qu, Yuan An Liu: Servo relays as distributed controllable-mobility network to maintain long-term stable links for mobile robot swarms.