Byeongho Heo

6

Papers

61

Total Citations

1

Affiliations

Affiliations

NAVER AI LAB

Papers (6)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

Masking meets Supervision: A Strong Learning Alliance

Morphing Tokens Draw Strong Masked Image Models

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

Token Bottleneck: One Token to Remember Dynamics