Matthew Yang

Welcome, welcome! I am a Master's student in the Machine Learning Department at Carnegie Mellon University working with Prof. Aviral Kumar. I'm interested in LLMs / VLMs and Reinforcement Learning.

Previously, I studied Computer Science and Statistics at the University of Waterloo. I have been extremely lucky to have worked with Prof. Gautam Kamath, Florian Kerschbaum, Yaoliang Yu, Jimmy Lin.

You can reach me at m[lastname]4@cs.cmu.edu.

CV  /  Google Scholar  /  Github  /  LinkedIn  /  X

(* denotes equal contribution)

Reinforcement Learning on LLMs

Self-Generated Credit Assignment in LLM Reasoning with Intervention Training Matthew Y. R. Yang, Hao Bai, Ian Wu, Gene Yang, Amrith Setlur, Aviral Kumar MATH-AI Workshop at NeurIPS 2025 paper

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Amrith Setlur*, Matthew Y. R. Yang*, Charlie Snell, Jeremy Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar EXAIT Workshop at ICML 2025 (Best Paper) paper / code / website

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning Yuxiao Qu*, Matthew Y. R. Yang*, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar ICML 2025 / FM‑Wild Workshop at ICLR 2025 (Oral) paper / code / website

Data Poisoning

Disguised Copyright Infringement of Latent Diffusion Models Yiwei Lu*, Matthew Y. R. Yang*, Zuoqiu Liu*, Gautam Kamath, Yaoliang Yu ICML 2024 paper / code

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors Yiwei Lu, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu SaTML 2024 paper / code

Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning William Xu, Yiwei Lu, Yihan Wang, Matthew Y. R. Yang, Gautam Kamath, Yaoliang Yu Reliable ML Workshop at NeurIPS 2025 paper

Information Retrieval & Differential Privacy

“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors Zhiying Jiang, Matthew Yang, Mikhail Tsirlin, Raphael Tang, Yiqin Dai, Jimmy Lin ACL 2023 paper / code

Integration of text and geospatial search for hydrographic datasets using the lucene search library Matthew Y. R. Yang, Siwen Yang, Jimmy Lin JCDL 2022 paper / code

Credits to Jon Barron for the website design.