publications

2024

2024

  1. Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization
    Sungbin Shin, Wonpyo Park, Jaeho Lee, Namhoon Lee
    EMNLP, 2024
    arXiv Code Poster Thread

2023

2023

  1. Critical Influence of Overparameterization on Sharpness-aware Minimization
    Sungbin Shin*, Dongyeop Lee*, Maksym Andriushchenko, Namhoon Lee
    arXiv preprint, 2023; ICML Workshop on High-dimensional Learning Dynamics, 2023
    Best paper award at JKAIA 2023
    arXiv Code Thread
  2. Semi-supervised Concept Bottleneck Models
    Jeeon Bae, Sungbin Shin, Namhoon Lee
    ICML Workshop on Artificial Intelligence and Human-Computer Interaction, 2023
    PDF Poster
  3. A Closer Look at the Intervention Procedure of Concept Bottleneck Models
    Sungbin Shin, Yohan Jo, Sungsoo Ahn, Namhoon Lee
    ICML, 2023; NeurIPS Workshop on TSRML, 2022
    arXiv Code Poster Thread