5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning
Researchers have identified a "flatness preference" in parameter-efficient fine-tuning (PEFT) methods, suggesting that a small subset of dimensions significantly impacts generalization. They propose Flatness Preference Optimization (FlatPO) to specifically target and flatten these key dimensions, aiming to improve overall model generalization. Experiments indicate that this approach enhances the effectiveness of various PEFT techniques. AI
IMPACT This research could lead to more efficient and effective fine-tuning of large multimodal models for specific tasks.