Awesome-Parameter-Efficient-Transfer-Learning

Why we included this project

Parameter-efficient fine-tuning moves fast enough that keeping up with the papers alone is a job. This curated index does the sorting for you: it groups a large body of research into a clear taxonomy, separating addition-based methods like adapters and prompt tuning from partial-based approaches and unified tuning, so you can compare techniques side by side instead of chasing scattered arXiv listings. Each entry links to the original paper and, where available, the authors' code, which matters when you want to reproduce a method or adapt it to your own vision or video task. The list also points to commonly used datasets and applications, so you get a sense of where each technique has been validated. It is a research reference rather than a drop-in library, best treated as a map for literature review and method selection.