alphaXiv @alphaxiv.org · May 3 Prisma Prisma is an open-source toolkit that brings powerful mechanistic interpretability tools—previously focused on language models—into the vision and video domain, enabling large-scale analysis and understanding of vision transformers.
0 likes 1 replies
?
Replies
I-Con I-Con introduces a single, unified information-theoretic framework that reveals a deep connection between over 23 different representation learning methods, showing they all minimize a form of KL divergence between supervisory and learned conditional distributions.