arXiv:2607. 05019v1 Announce Type: new Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks.
By Ilya Burenko, Dmitry Vetrov
arXiv:2608. 02769v1 Announce Type: cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance.
By Sagnik Nandy, Samriddha Lahiry, Pragya Sur, Subhabrata Sen
arXiv:2607. 27289v1 Announce Type: new Abstract: The promise of multimodal fusion lies in combining complementary sources of evidence, yet more evidence does not always yield a better prediction.
By Yu Chang, Anzhe Cheng, Chenwei Wu, Zhuoran Wang, Jiahao Chen, Tamoghna Chattopadhyay, Sophia I. Thomopoulos, Paul M. Thompson, Liyue Shen, Paul Bogdan
arXiv:2606. 11190v1 Announce Type: new Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality.
By Ilay Kamai, Hugues Van Assel, Aviv Regev, Hagai B. Perets, Randall Balestriero
InfMasking introduces a unified multimodal learning framework that uses Infinite Masking to encourage fusion modules to capture synergistic information across modalities. By randomly masking modality features before fusion and enforcing consistency with an unmasked reference, the method discourages reliance on dominant or shared signals and promotes meaningful cross‑modal interactions. The approach models masked fused representations as Gaussian, optimizing closed‑form variational bounds, and demonstrates improved predictive performance and higher synergy metrics on benchmark datasets.
By Liangjian Wen, Qun Dai, Jiang Duan, Yong Dai, Jianzhuang Liu, Dongkai Wang, Jun Wang, Fuyuan Cao, Zenglin Xu, Zhao Kang
Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality. We develop a unified linear framework that addresses both questions.