Home › Research Papers › LoRA: Low-Rank Adaptation (2021)
LoRA: Low-Rank Adaptation (2021)
Research Paper
Systems
Fine-tuning for the GPU-poor — tiny adapters instead of full weights.
You're looking at a research-paper record: a landmark paper and what it introduced to the field.
Microsoft researchers showed models adapt through low-rank update matrices a thousandth the size of the weights — making fine-tuning accessible to anyone with one GPU and creating the adapter ecosystems around Llama and Stable Diffusion.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Introduced in
Basis for
Sources
Record reviewed as of 2026-01-15 — see Methodology.