Sungbin Shin

According to our database, Sungbin Shin authored at least 3 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization.

Sungbin Shin, Wonpyo Park, Jaeho Lee, Namhoon Lee

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

The Effects of Overparameterization on Sharpness-aware Minimization: An Empirical and Theoretical Analysis.

Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee

CoRR, 2023

A Closer Look at the Intervention Procedure of Concept Bottleneck Models.

Sungbin Shin, Yohan Jo, Sungsoo Ahn, Namhoon Lee

Proceedings of the International Conference on Machine Learning, 2023