Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Dynamic Rank Adjustment for Accurate and Efficient Neural Network Training
Hyuntak Shin, Aecheon Jung, Sungeun Hong +1
Low-rank training methods reduce the number of trainable parameters by re-parameterizing the weights with matrix decompositions (e.g., singular value decomposition). However, enfor…
cs.LG2025
Task Vector Quantization for Memory-Efficient Model Merging
Youngeun Kim, Seunghwan Lee, Aecheon Jung +2
Model merging enables efficient multi-task models by combining task-specific fine-tuned checkpoints. However, storing multiple task-specific checkpoints requires significant memory…
cs.LG2024
SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
Aecheon Jung, Seunghwan Lee, Dongyoon Han +1
Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding task interference. We argue that i…