2 papers
cs.CV2025
ABM-LoRA: Activation Boundary Matching for Fast Convergence in Low-Rank Adaptation
Dongha Lee, Jinhee Park, Minjun Kim +1
We propose Activation Boundary Matching for Low-Rank Adaptation (ABM-LoRA), a principled initialization strategy that substantially accelerates the convergence of low-rank adapters…
cs.CV2025
Real-Aware Residual Model Merging for Deepfake Detection
Jinhee Park, Guisik Kim, Choongsang Cho +1
Deepfake generators evolve quickly, making exhaustive data collection and repeated retraining impractical. We argue that model merging is a natural fit for deepfake detection: unli…