Publications

Preprints

• Preserve-and-Compose Training for Composed Image Retrieval
  Sehyun Kwon, 2026.
  paper / code

• SpreadRAG: Geometric Bottleneck of Single-Vector Retrieval in Multi-Hop RAG
  Sahngmin Yoo, Sehyun Kwon†, 2026.

Journal Papers

• Task Diversity Shortens the In-context Learning Plateau
  Jaeyeon Kim*, Sehyun Kwon*, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu, Transactions on Machine Learning Research (TMLR), 2025.
  paper / code

Conference Papers

• Image Clustering Conditioned on Text Criteria
  Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee, International Conference on Learning Representations (ICLR), 2024.
  paper / code

• Rotation and Translation Invariant Representation Learning with Implicit Neural Representations
  Sehyun Kwon, Joo Young Choi, Ernest K. Ryu, International Conference on Machine Learning (ICML), 2023.
  paper / code

• WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
  Albert No, TaeHo Yoon, Sehyun Kwon, Ernest K. Ryu, International Conference on Machine Learning (ICML), 2021.
  paper / code

Workshop Papers

• Diffusion Probabilistic Models Generalize when They Fail to Memorize
  TaeHo Yoon, Joo Young Choi, Sehyun Kwon, Ernest K. Ryu, ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023.
  paper