Tingyu Qu*

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks

"Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter, project a model’s hidden states to a lower dimension, allowing pre-trained models to adapt to new data through this low-rank bottleneck. However, PEFT tasks involving multiple modalities, like vision-language (VL) t…