2026
ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning
CVPR 2026
Tensor-based methods have attracted growing interest due to their ability to reduce trainable parameters and offer advantages over matrix-based approaches in parameter-efficient fine-tuning (e.g., LoRA and PiSSA), particularly in capturing inter-layer correlations. However, directly applying tensor