Picture for Jun-Hyung Park

Jun-Hyung Park

Korea University

C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning

Add code
Nov 01, 2024
Viaarxiv icon

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science

Add code
Oct 19, 2024
Viaarxiv icon

Zero-shot Commonsense Reasoning over Machine Imagination

Add code
Oct 12, 2024
Viaarxiv icon

DIVE: Towards Descriptive and Diverse Visual Commonsense Generation

Add code
Aug 15, 2024
Viaarxiv icon

Dynamic Structure Pruning for Compressing CNNs

Add code
Mar 17, 2023
Viaarxiv icon

Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking

Add code
Dec 15, 2022
Viaarxiv icon