LoRA can Replace Time and Class Embeddings in Diffusion Probabilistic Models

[PDF] arxiv.org

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models

A Kasymov, M Sendera, M Stypułkowski… - arXiv preprint arXiv …, 2024 - arxiv.org
Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional
generative diffusion models. LoRA utilizes a small number of context examples to adapt the …
被引用次数：1 相关文章 所有 3 个版本
[PDF] arxiv.org

LoRA Training in the NTK Regime has No Spurious Local Minima

U Jang, JD Lee, EK Ryu - arXiv preprint arXiv:2402.11867, 2024 - arxiv.org
Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-
tuning of large language models (LLM), but our theoretical understanding of LoRA has been …
被引用次数：12 相关文章 所有 3 个版本