← Search

Wanglong Lu

2 accepted papers

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…

Cited by 0SourcecodeScholar
2024

Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework

ECCV 2024poster

"Recently, numerous tensor singular value decomposition (t-SVD)-based tensor recovery methods have shown promise in processing visual data, such as color images and videos. However, these methods often suffer from severe performance degradation when confronted with tensor data exhibiting non-smooth…