AI RESEARCH
Self-Soupervision: Cooking Model Soups without Labels
arXiv CS.LG
•
ArXi:2602.02890v2 Announce Type: replace Model soups are strange and strangely effective combinations of parameters. They take a model (the stock), fine-tune it into multiple models (the ingredients), and then mix their parameters back into one model (the soup) to improve predictions. While all known soups require supervised learning, and optimize the same loss on labeled data, our recipes for Self-Soupervision generalize soups to self-supervised learning (SSL). Our Self-Souping lets us flavor ingredients on new data sources, e.g.