The paper introduces Layerwise Importance Sampled AdamW (LISA) as a memory-efficient alternative to Low-Rank Adaptation (LoRA) for large language models, outperforming both in various fine-tuning tasks.

https://arxiv.org/abs//2403.17919

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers