RRLoRA: Refactorized Low-Rank Adaptation With Learning-Rate Restarts for Efficient Fine-Tuning
Low-rank adaptation (LoRA) has become a standard parameter-efficient fine-tuning technique for adapting large foundation models. However, prior work has shown that LoRA training dynamics and final performance are sensitive to initialization, and state-of-the-art data-driven initializations often inc...
Sábháilte in:
| Príomhchruthaitheoirí: | , |
|---|---|
| Formáid: | Artigo |
| Teanga: | Inglês |
| Foilsithe / Cruthaithe: |
IEEE
2026-01-01
|
| Sraith: | IEEE Access |
| Ábhair: | |
| Rochtain ar líne: | https://ieeexplore.ieee.org/document/11547155/ |
| Clibeanna: |
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!
|