AI RESEARCH
Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
arXiv CS.CV
•
ArXi:2605.22679v1 Announce Type: new Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which compromises the original geometry and