Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion 事件

Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion arXiv:2601.21670v3 Announce Type: replace Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dominating the others. However, balanced optimization does not fully determine the geometry of intermediate representations. Supervised multimodal models may still learn low-diversity modality-specific embeddings or allow paired cr