MoMoVL: Modality-Aware Adaptive Compression for On-Device Sparsely-Activated Vision-Language Models

arXiv:2611.23695 · cs.CV, cs.LG · Submitted 2026-11-18 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-11-18

Updated: 2026-11-18

Related papers