Poster Sat, Sep 12, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 381

VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning

Mingkang Dong ⋅ Hongyi Cai ⋅ jie li ⋅ Sifan Zhou ⋅ Bin Ren ⋅ Kunyu Peng ⋅ Yuqian Fu

Keywords: Federated, Continual & Efficient Learning; Model Security

Project Page