Research

2026

• Leveraging user-to-user social similarity graphs for multi-valued rating matrix completion.
  Jeonghwan Lee.
  

  Under review (available upon request), 2026.
  

• From Knowledge to Action: Outcomes of the 2025 Large Language Models (LLM) Hackathon for Applications in Materials Science and Chemistry.
  Aritra Roy et al (A detailed list of contributors can be found in the appendix of the paper).
  

  Preprint (to appear on arXiv, available upon request), 2026.
  

2025

• Learning bounds for doubly-robust covariate shift adaptation.
  Jeonghwan Lee and Cong Ma.
  

  arXiv preprint arXiv:2511.11003, 2025. (arXiv) (PDF)
  

2024

• Off-policy estimation with adaptively collected data: the power of online learning.
  Jeonghwan Lee and Cong Ma.
  

  The 38th Annual Conference on Neural Information Processing Systems (NeurIPS), Dec. 2024. (arXiv) (PDF)
  

• A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits.
  Doyeon Kim*, Jeonghwan Lee*, and Hye Won Chung.
  

  IEEE Transactions on Information Theory, vol. 70, no. 3, pp. 2076-2117, Mar. 2024. (arXiv) (PDF)
  

2022

• A Generalized Worker-Task Specialization Model for Crowdsourcing: Optimal Limits and Algorithm.
  Doyeon Kim*, Jeonghwan Lee*, and Hye Won Chung.
  

  The proceedings of IEEE International Symposium on Information Theory (ISIT), pp. 1483-1488, Jul. 2022. (PDF)
  

2020

• Robust Hypergraph Clustering via Convex Relaxation of Truncated MLE.
  Jeonghwan Lee, Daesung Kim, and Hye Won Chung.
  

  IEEE Journal On Selected Areas in Information Theory (JSAIT), vol. 1, no. 3, pp. 613-631, Nov. 2020. (arXiv) (PDF)
  

* denotes either the equal contribution or the alphabetical ordering.