Yunxiang Yan
Yunxiang (δΊηΏ) is a final-year MSCSE student at Georgia Institute of Technology, advised by Prof. Kartik Goyal on natural language processsing.
He has also been fortunate to work with Prof. Meng Jiang on graph sampling and anomaly detection as an REU at the University of Notre Dame DM2 Lab.
His current research focuses on scalable, contamination-robust evaluation of language models and interpretability & control of chain-of-thought reasoning.
His future research interest includes:
- Evaluate and understand language models in open-ended, long-form domains
- Build (semi-) autonomous agents for creative tasks such as narrative generation
news
| Dec 13, 2025 | I graduated from Georgia Tech with a master of science degree in CSE! ππ |
|---|---|
| Oct 25, 2025 | My first-author paper Cascaded Information Disclosure for Generalized Evaluation of Problem Solving Capabilities got accepted by IJCNLP-AACL as Main Conference Paper. π₯³ |
selected publications
- IJCNLP-AACLCascaded Information Disclosure for Generalized Evaluation of Problem Solving CapabilitiesIn Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2025), 2025To appear
- KDDConstructing and Sampling Directed Graphs with Linearly Rescaled Degree MatricesIn Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD β22) Undergraduate Consortium, 2022Poster Presentation