|
2022

Contrastive Adapters for Foundation Model Group Robustness

M. Zhang, et al.

Abstract

The authors propose Contrastive Adapting, an efficient adapter training strategy that improves the group robustness of large pretrained foundation models (FMs) without finetuning, leading to up to 56.0 percentage points of increase in accuracy compared to zero-shot.

Share this article
Coming Fall 2026
ImageImage
A one-day, invite-only summit providing a first look at the benchmarks and research that will shape the frontier. Sign up for updates.