Preprint
Aug 2026
Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion
This work proposes Inverted Asymmetric Fusion (IAF), which avoids forcing mutual attention across modalities, and shows that IAF preserves the dominant modality's internal accuracy at its unimodal ceiling across all tested configurations.
Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat
· 0 citations