Reproduce “Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Zhuofan Xie, Zishan Lin, Jinliang Lin, Jie Qi, Shaohua Hong, Shuo Li

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.