Ming Li

I am a third-year Ph.D. student in Computer Science at the University of Maryland, advised by Prof. Tianyi Zhou. I began my academic journey in computer science with a Bachelor of Science from Xi’an Jiaotong University in 2020, followed by a Master of Science at Texas A&M University advised by Prof. Ruihong Huang in 2023. Besides, I spent 2 years at Shenzhen Institutes of Advanced Technology, Chinese Academy of Science, advised by Prof. Yu Qiao since 2019.

If you are looking for a highly motivated intern with a background in computer science and a passion for advancing AI technologies, I would be thrilled to have an opportunity to chat with you!

My research interests broadly lie in the areas of Machine Learning (ML), Natural Language Processing (NLP), and Large Language Models (LLM).
More specifically, my recent research interests mainly lie in:
(1). Data-Centric AI, including Data Synthesis and Selection: (Cherry LLM (IFD), Superfiltering, Mosaic-IT, Selective Reflection-Tuning);
(2). Interpretability, including Training Effects and Response Analysis: (Layer_Gradient, Gradient_Unified, MiP-Overthinking, ThinkARM);
(3). Human-AI Cognitive Alignment: (Difficulty Alignment, Schoenfeld Reasoning);
(4). AI for Education: (Item Difficulty Modeling, Position: Student Simulation).

I am really interested in collaboration, feel free to drop me an email for any opportunity!

news

Jan 22, 2026	I was awarded the 2026 Apple Fellowship!
Dec 23, 2025	One paper was put on the arXiv: Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models.
Dec 21, 2025	One paper was put on the arXiv: Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction.
Nov 17, 2025	One paper was selected as a LAW Workshop @ NeurIPS 2025 Spotlight paper! CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning.
Sep 18, 2025	Two papers were accepted by NeurIPS 2025! See you in San Diego! 1 ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness; 2 ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs;
Aug 20, 2025	Two papers were accepted by EMNLP 2025! 1 Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory; 2 DISCO Balances the Scales: Adaptive Domain-and Difficulty-Aware Reinforcement Learning on Imbalanced Data;
Jul 07, 2025	One papers were accepted by COLM 2025! Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
Jun 23, 2025	One paper was put on the arXiv: CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning. Repo: CaughtCheating.
Jun 18, 2025	Start serving as an ACL ARR Area Chair!
Jun 08, 2025	One paper was put on the arXiv: What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding.
May 16, 2025	Three papers were accepted by ACL 2025! 1 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective (Oral); 2 Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning; 3 ATLaS: Agent Tuning via Learning Critical Steps.
Apr 20, 2025	I will join Amazon (Palo Alto) for AS Internship this summer~ Happy to connect!
Apr 14, 2025	One paper was put on the arXiv: How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients. Repo: Gradient_Unified.
Mar 05, 2025	One paper was accepted by Reasoning and Planning for LLMs @ ICLR2025! Towards visual text grounding of multimodal large language model.
Jan 28, 2025	I will join Microsoft (MSR) as a Research Internship this spring semester~
Jan 22, 2025	One paper was accepted by NAACL 2025! RuleR: Improving LLM Controllability by Rule-based Data Recycling
Jan 22, 2025	One paper was accepted by ICLR 2025! BenTo: Benchmark Task Reduction with In-Context Transferability
May 16, 2024	Three papers were accepted by ACL 2024! 1 Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning; 2 Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning; 3 Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements (DEBATunE).
Mar 13, 2024	One paper was accepted by NAACL 2024! From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning (Cherry LLM (IFD))
Feb 21, 2024	I will join Adobe (based in San Jose) as a Research Scientist/Engineer Intern this Summer~
Oct 28, 2023	One paper was accepted by Instruction Workshop @ NeurIPS 2023! Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning.
Oct 07, 2023	One paper was accepted by EMNLP 2023! PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter.
Sep 01, 2023	I arrived at the University of Maryland, officially beginning my journey for a Ph.D. ✌️
Jun 01, 2023	I obtained my Master’s in Computer Science at Texas A&M University.