Hi, I’m Yuxiao Qu

Email: yuxiaoq(at)andrew.cmu.edu
Office: Gates and Hillman Center 8113

I am a second-year PhD in the Machine Learning Department, School of Computer Science at Carnegie Mellon University, advised by Prof. Aviral Kumar and Prof. Ruslan Salakhutdinov. My PhD is generously supported by Amazon AI Ph.D. Fellowship. I am also a part-time student researcher at NVIDIA Research.

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.

Email  /  CV  /  Google Scholar  /  GitHub  /  Twitter

(Updated: March 2026)

• Jan 26, 2026: One paper RLAD is accepted by ICLR 2026.
• Dec 9, 2025: I am invited to give a talk at the The 5th Workshop on Mathematical Reasoning and AI on our recent work Learning to Reason on Hard Problems with Privileged On-Policy Exploration.
• Aug 25, 2025: I am honoured to receive the Amazon AI Ph.D. Fellowship.
• May 1, 2025: One paper MRT: Meta Reinforcement Finetuning is accepted by ICML 2025.
• April 26, 2024: I am invited to give an oral presentation at FM-Wild @ ICLR 2025 on our recent work MRT: Meta Reinforcement Finetuning.
• Sep 25, 2024: One paper Recursive Introspection is accepted by NeurIPS 2024.
• July 27, 2024: I am invited to give a contributed talk at Large Language Models and Cognition @ ICML 2024 on our recent work Recursive Introspection.
• May 14, 2024: One Paper Guided Data Augmentation is accepted by RLC 2024.
• May 13, 2024: I started my PhD at Carnegie Mellon University.
• August 21, 2023: I started my Master at Carnegie Mellon University.
• April 17, 2023: I joined the research computing team at the Morgridge Institute for Research as a Research Software Engineer.
• December 25, 2022: I graduated from the University of Wisconsin-Madison.

• Reviewer: ICML 2024, NeurIPS 2024, ICLR 2025, AISTATS 2025