Seongmin Park (박성민)

Biography

I'm a Ph.D. student in the Department of Artificial Intelligence at Sungkyunkwan University (SKKU), Korea. I received my B.S. degree in Mechanical Engineering from SKKU in 2020. 

Favorite quote

"We have two lives, and the second begins when we realize we only have one."  - Confucius

Publications

• MergeRec: Model Merging for Data-Isolated Cross-Domain Sequential Recommendation [code]
  Hyunsoo Kim*, Jaewan Moon*, Seongmin Park, Jongwuk Lee  (* : equal contribution)
  The 32nd International ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
  Jeju, Korea, August 9-13, 2026 (To appear)

• Enhancing Time Awareness in Generative Recommendation [paper] [code]
  Sunkyung Lee, Seongmin Park, Jonghyo Kim, Mincheol Yoon, Jongwuk Lee
  The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP Findings)
  Suzhou, China, November 5-9, 2025

• MUFFIN: Mixture of User-Adaptive Frequency Filtering for Sequential Recommendation [paper] [code]
  Ilwoong Baek*, Mincheol Yoon*, Seongmin Park, Jongwuk Lee (* : equal contribution)
  The 34th ACM International Conference on Information and Knowledge Management (CIKM)
  Seoul, Republic of Korea, November 10-14, 2025 (Acceptance Rate: 27%, 443/1627)

• LLM-Enhanced Linear Autoencoders for Recommendation [paper] [code]
  Jaewan Moon*, Seongmin Park*, Jongwuk Lee (* : equal contribution)
  The 34th ACM International Conference on Information and Knowledge Management (CIKM, short paper)
  Seoul, Republic of Korea, November 10-14, 2025 (Acceptance Rate: 30.6%, 185/604)

• Why is Normalization Necessary for Linear Recommenders? [paper] [code]
  Seongmin Park, Mincheol Yoon, Hye-young Kim, Jongwuk Lee
  The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
  Padua, Italy, July 13-17, 2025 (Acceptance Rate: 21.5%, 238/1105)

• Linear Item-Item Models with Neural Knowledge for Session-based Recommendation [paper] [code]
  Minjin Choi, Sunkyung Lee, Seongmin Park, Jongwuk Lee
  The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
  Padua, Italy, July 13-17, 2025 (Acceptance Rate: 21.5%, 238/1105)

• Empowering Retrieval-based Conversational Recommendation with Contrasting User Preferences [paper] [code]
  Heejin Kook*, Junyoung Kim*, Seongmin Park, Jongwuk Lee (* : equal contribution)
  2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)
  Albuquerque, New Mexico, USA, April 29-May 4, 2025 (Acceptance Rate: 22.15%, 719/3246)

• Temporal Linear Item-Item Model for Sequential Recommendation [paper] [code]
  Seongmin Park*, Mincheol Yoon*, Minjin Choi, Jongwuk Lee (* : equal contribution)
  The 18th ACM International Conference on Web Search and Data Mining (WSDM)
  Hannover, Germany, March 10-14, 2025 (Acceptance Rate: 17.3%, 106/614, Oral Presentation (Top 6.5%))

• Toward a Better Understanding of Loss Functions for Collaborative Filtering [paper] [code]
  Seongmin Park, Mincheol Yoon, Jae-woong Lee, Hogun Park, Jongwuk Lee
  The 32nd ACM International Conference on Information and Knowledge Management (CIKM)
  Birmingham, UK, October 21-25, 2023 (Acceptance Rate: 24%, 354/1472)

• uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering [paper] [code]
  Jae-woong Lee, Seongmin Park, Mincheol Yoon, Jongwuk Lee
  The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR, short paper)
  Taipei, Taiwan, July 23-27, 2023 (Acceptance Rate: 25.12%, 154/613)

• Bilateral Self-unbiased Learning from Biased Implicit Feedback [paper] [code]
  Jae-woong Lee, Seongmin Park, Joonseok Lee, Jongwuk Lee
  The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
  Madrid, Spain, July 11-15, 2022 (Acceptance Rate: 20%, 161/794)

• Dual Unbiased Recommender Learning for Implicit Feedback [paper] [code]
  Jae-woong Lee, Seongmin Park, Jongwuk Lee
  The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR, short paper)
  Online (Virtual Event), July 11-15, 2021 (Acceptance Rate: 27.6%, 145/526)

• 추론 경로를 통한 거대언어모델 기반 제로샷 대화형 추천시스템 성능 개선 [paper]
  국희진, 박성민, 이종욱
  정보과학회논문지 (Journal of KIISE) Vol.52 No.7 [2025]: 617-626, Jul 2025

• 사고 연쇄 프롬프팅을 통한 거대 언어 모델의 영화 도메인에 대한 지식 평가 및 분석 [paper]
  나정우*, 국희진*, 박성민, 문재완, 이종욱 (* : equal contribution)
  한국정보과학회 학술발표논문집, Jun 2022

More information

Personal Website

LinkedIn

CV