When Does Sharing Work? Scaling a Shared SigLIP2 Across Image, Video, Audio, and Audio-Visual Representations

arXiv:2611.05406 · cs.CV, cs.AI · Submitted 2026-10-20 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-10-20

Updated: 2026-10-20

Terminology

Sources

Related papers