Muhan Gao | Texas A&M University

About Me

I am a first-year PhD student at Texas A&M University, advised by Kuan-Hao Huang in FLAIR Lab.

Before coming to Texas A&M, I finished my master degree at Johns Hopkins University, where I was fortunately advised by Prof.Daniel Khashabi in the Center for Language and Speech Processing.

LCLMs Evaluation: LLM’s long-context ability is more than simple retrieval, but how can we better evaluate and understand it?
Mechanistic Methods to Improve LLMs: Can we understand long-context sequence processing internally, and how to improve it?

[May. 2026] Our paper about long context and context rot: The First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning is accepted to ICML 2026.
[Aug. 2025] Our paper about In-context learning: ICL CIPHERS: Quantifying “Learning” in In-Context Learning via Substitution Ciphers is accepted to EMNLP 2025.
[Apr. 2025] Science Hierarchography: Hierarchical Organization of Science Literature is released on Arxiv!
[Aug. 2024] Our paper about long-context problem: Insights into LLM Long-Context Failures: When Transformers Know but Don’t Tell is accepted to EMNLP 2024.

Reviewers: ARR since Feb 2025, NeurIPS 2025, ICLR 2026, ICML 2026 (Gold Reviewer), COLM 2026