2026
Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond
AAAI 2026technical
Little research explores the correlation between the expressive ability and generalization ability of the low-rank adaptation (LoRA). Sharpness-Aware Minimization (SAM) improves model generalization for both Convolutional Neural Networks (CNNs) and Transformers by encouraging convergence to locally