We stand with Ukraine  

Minglai Yang

Affiliations:
  • University of Arizona, Tucson, AZ, USA


According to our database1, Minglai Yang authored at least 6 papers in 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
AlignSAE: Concept-Aligned Sparse Autoencoders.
[BibTeX]
[DOI]
Minglai Yang
,
Xinyu Guo
,
Mihai Surdeanu
,
Liangming Pan
CoRR, December, 2025

Peeking inside the Black-Box: Reinforcement Learning for Explainable and Accurate Relation Extraction.
[BibTeX]
[DOI]
Xinyu Guo
,
Zhengliang Shi
,
Minglai Yang
,
Mahdi Rahimi
,
Mihai Surdeanu
CoRR, October, 2025

Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM.
[BibTeX]
[DOI]
Thang Duong
,
Minglai Yang
,
Chicheng Zhang
CoRR, May, 2025

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality.
[BibTeX]
[DOI]
Razvan-Gabriel Dumitru
,
Minglai Yang
,
Vikas Yadav
,
Mihai Surdeanu
CoRR, February, 2025

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark.
[BibTeX]
[DOI]
Minglai Yang
,
Ethan Huang
,
Liang Zhang
,
Mihai Surdeanu
,
William Yang Wang
,
Liangming Pan
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste.
[BibTeX]
[DOI]
Razvan-Gabriel Dumitru
,
Minglai Yang
,
Vikas Yadav
,
Mihai Surdeanu
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025


  Loading...