Poster Sat, Sep 12, 2026 • 6:00 AM – 8:00 AM PDT ExHall # 140

Semantic Generative Tuning for Unified Multimodal Models

Songsong Yu ⋅ Yuxin Chen ⋅ Ying Shan ⋅ Yanwei Li

Keywords: Multimodal, Video & Document Understanding