3 papers
cs.LG2026
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…
cs.CV2025
Instance-Aware Test-Time Segmentation for Continual Domain Shifts
Seunghwan Lee, Inyoung Jung, Hojoon Lee +2
Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or…
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…