Minglai Yang

I study how to understand and enhance LLM reasoning. 印章

prof_big.jpg

📧 mingly@arizona.edu

💼 Harvill 454

📍 Tucson, AZ 85721, USA

I am a final year undergraduate student at the Computer Science, University of Arizona (GPA: 4.0/4.0) and am on track to complete my Bachelor’s degree just over 2 years (Fall 2025). As Founder & President of AI Club at UA, I run workshops, onboard incoming students, and lead industry collaborations. In our CS department, I currently serve as both TA (Discrete Math I & II) and RA in CLULAB, IVILAB and ML4AI LAB.

My research interests focus on NLP, mechanistic interpretability and machine learning. Specifically, I study how to build LMs reasoning robustly under noise, improve reasoning efficiency through copying, analyze LLM planning in real-world tasks and uncover their internal reasoning mechanism with Sparse Autoencoders. I am fortunate to conduct research advised by Prof. Liangming Pan, Prof. Mihai Surdeanu and Prof. Kobus Barnard. In addition, I also collaborate with Prof. William Wang, Prof. Adarsh Pyarelal, and Prof. Chicheng Zhang.

I previously worked as a Machine Learning Engineer intern at CoreTechs. This summer, I was a research intern at Knowledge Engineering Group (KEG), Tsinghua University, supervised by Prof. Juanzi Li, working on LLM reasoning mechanism.

🎓
PhD Applications – Fall 2026

I am applying to PhD programs in NLP, interpretability, and cognitive science for Fall 2026. My goal is to develop LLMs that reason more robustly, efficiently, and transparently. If you’re working in this space, I’d love to connect!


news

Aug 20, 2025 Both of my submissions were accepted to EMNLP 2025 Main 🎉 (Acceptance Rate: 22.16%). Grateful to all my co-authors, with special thanks to Profs. Liangming Pan, Mihai Surdeanu and William Wang.
Jun 05, 2025 I will be a research intern at THUKEG, Department of CS in Tsinghua University this summer advised by Prof. Juanzi Li, focusing on reasoning mechanism.
May 09, 2025 Galileo Circle Scholar, University of Arizona — Top 0.8% academic award.
Feb 18, 2025 As President of the AI Club at the University of Arizona, I led the club to raise over $12,000.
Dec 03, 2024 Excited to receive an RAship! I’ll lead a project advised by Liangming Pan and collaborate with William Wang at UCSB NLP Group.
Nov 01, 2024 I’m featured in our department newsletter! Huge thanks to Rishu Singh for the shoutout.
Oct 03, 2024 I’ve joined the Computational Language Understanding Lab (CLULAB)! I’m grateful to be advised by Mihai Surdeanu working on NLP and efficient LLMs.
May 09, 2024 I’m starting a new position as Machine Learning Engineer Intern at CoreTechs!
Mar 14, 2024 I’m starting a new position as AI Engineer in AI Core, the University of Arizona.
Sep 27, 2023 Became a research assistant under the guidance of Dr. Kobus Barnard in the Interdisciplinary Visual Intelligence Lab.

selected publications

  1. How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark
    Minglai Yang, Ethan Huang , Liang Zhang, Mihai SurdeanuWilliam Wang, and Liangming Pan
    Oral Presentation
    EMNLP Main Conference , 2025
  2. CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
    Razvan-Gabriel Dumitru, Minglai YangVikas Yadav, and Mihai Surdeanu
    Oral Presentation
    EMNLP Main Conference , 2025
  3. Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM
    Thang Duong, Minglai Yang, and Chicheng Zhang
    Exploration in AI Today (EXAIT) Workshop @ ICML , 2025