Poster Fri, Sep 11, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 59

From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion

pengpeng Zeng ⋅ Yuyu Guo ⋅ Pengpeng Zeng ⋅ Jingkuan Song ⋅ Peng Di ⋅ Hang Yu ⋅ Lianli Gao

Keywords: Vision Foundation Models: Interpretability and Reasoning