← Search

Jenna L. Ballard

2 accepted papers

2025

$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

ICML 2025poster

Modality fusion is a cornerstone of multimodal learning, enabling information integration from diverse data sources. However, existing approaches are limited by $\textbf{(a)}$ their focus on modality correspondences, which neglects heterogeneous interactions between modalities, and $\textbf{(b)}$ th…

2025

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

ICML 2025poster

Medical multi-modal learning requires an effective fusion capability of various heterogeneous modalities. One vital challenge is how to effectively fuse modalities when their data quality varies across different modalities and patients. For example, in the TCGA benchmark, the performance of the same…

Cited by 0SourcePDFScholar