Low-Rank Adaptation

Concept

A method commonly used in LLMs and now in image generation, which trains only a fraction of model weights by considering them as a base model's weights plus two low-rank matrices, preserving performance while reducing training cost.

Mentioned in 1 video

Videos Mentioning Low-Rank Adaptation

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training

Stanford Online

A method commonly used in LLMs and now in image generation, which trains only a fraction of model weights by considering them as a base model's weights plus two low-rank matrices, preserving performance while reducing training cost.