About

I’m a Ph.D. student at UIUC. My goal is to build intelligent information systems for decision support tailored to each individual, built on three axes: effectiveness, personalization, and lifelong learning. Always open to collaboration, so feel free to reach out!

Research interests: Recommender Systems · Agentic Search & Memory · Personalization · Continual Learning

News

  • 2026–08Accepted at CIKM’26 Continual retriever-reranker distillation for LLM recommendation.
  • 2026–07Accepted at COLM’26 Uncertainty-aware reward factorization for LLM personalization.
  • 2026–06Internship at Amazon Applied Scientist Intern, Prime AI/ML Science.
  • 2026–04Accepted at SIGIR’26 LLM-based intent refinement for session-based recommendation.
  • 2025–10Accepted at WSDM’26 Continual sequential recommendation from data streams.

Education

Aug 2025 – Present

Ph.D., Information Sciences, UIUC (Advisor: Prof. Jingrui He)

Feb 2022 – Feb 2024

M.S., Artificial Intelligence, POSTECH (Advisor: Prof. Hwanjo Yu)

Mar 2015 – Feb 2022

B.S., Computer Science / Mathematics and Statistics, HGU (Magna Cum Laude)

Experience

Jun 2026 – Sep 2026

Applied Scientist Intern, Amazon Cold-start problem in large-scale recommender systems (manager: Shreya Chakrabarti)

Apr 2025 – Aug 2025

Visiting Researcher, Korea University LLM-generated intents for session-based recommendation (SIGIR 2026, host: Prof. SeongKu Kang)

Sep 2023 – Feb 2024

Visiting Researcher, University of Virginia Collaborative diffusion models for recommender systems (WWW 2025, host: Prof. Jundong Li)

Aug 2022 – Feb 2023

Visiting Researcher, Carnegie Mellon University IITP AI Intensive Program, sponsored by the Korean government

Selected Publications

first-authored * equal contribution
  • [1]

    SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation

    Seunghyun Baek*, Gyuseok Lee*, Seunghan Lee, Wonbin Kweon, Dong Wang, SeongKu Kang

    CIKM 2026 · paper · code

  • [2]

    Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization

    Gyuseok Lee, Wonbin Kweon, Zhenrui Yue, SeongKu Kang, Jiawei Han, Dong Wang

    COLM 2026 · paper · code

  • [3]

    SPRINT: Scalable and Predictive Intent Refinement for LLM-Enhanced Session-Based Recommendation

    Gyuseok Lee, Wonbin Kweon, Zhenrui Yue, Yaokun Liu, Yifan Liu, Susik Yoon, Dong Wang, SeongKu Kang

    SIGIR 2026 · paper · code

  • [4]

    Capturing User Interests from Data Streams for Continual Sequential Recommendation

    Gyuseok Lee, Hyunsik Yoo, Junyoung Hwang, SeongKu Kang, Hwanjo Yu

    WSDM 2026 · paper · code

  • [5]

    Collaborative Diffusion Model for Recommender System

    Gyuseok Lee, Yaochen Zhu, Hwanjo Yu, Yao Zhou, Jundong Li

    WWW 2025 · Short Paper · paper · code

  • [6]

    Continual Collaborative Distillation for Recommender System

    Gyuseok Lee*, SeongKu Kang*, Wonbin Kweon, Hwanjo Yu

    KDD 2024 · paper · code

Miscellaneous

life outside research

I’ve been training for distance races, and finished my first 10K this April. Aiming for a half marathon next year.

Crossing the finish line at Memorial Stadium, Illinois Marathon weekend
Illinois Marathon weekend, Memorial Stadium
Race tracker showing a 10K finish time of 1:00:06
First 10K, 1:00:06
Race bib, Christie Clinic Illinois 10K, number 17543
Race bib, Illinois 10K