Dongyoon Han

8

Papers

138

Total Citations

2

Affiliations

Affiliations

NAVER AI LabKAIST

Papers (8)

Model Stock: All we need is just a few fine-tuned models

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Masking meets Supervision: A Strong Learning Alliance

Morphing Tokens Draw Strong Masked Image Models

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

SeiT++: Masked Token Modeling Improves Storage-efficient Training

Token Bottleneck: One Token to Remember Dynamics