Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...

Join the conversation