نسخة أولية وصول مفتوح
Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA
While Low-Rank Adaptation (LoRA) enables efficient task specialization, its learned updates can compromise capabilities beyond the target task. We identify \textbf{adaptation imbalance}: a few singular directions dominate the trained update, leaving its performance sensitive to how gains are allocated. We argue that \t …