StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
NeurIPSSpotlight2025
TL;DR
Low-rank adaptation (LoRA) has been widely adopted as a parameter-efficient technique for fine-tuning large-scale pre-trained models…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
fine-tuning efficient
← All NeurIPS 2025 Spotlight papers · Browse the whole archive