2025
AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
NeurIPS 2025poster
In this paper, we propose AdaMSS, an adaptive multi-subspace approach for parameter-efficient fine-tuning of large models. Unlike traditional parameter-efficient fine-tuning methods that operate within a large single subspace of the network weights, AdaMSS leverages subspace segmentation to obtain…