SOURCE-LINKED INTELLIGENCE

RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Image-metadata prediction requires fusing heterogeneous evidence whose reliability can vary across samples and latent factors. Existing representation-level fusion methods typically choose an aggregation architecture, such as concatenation, gating, conditional modulation, or attention, without explicitly defining what the fused representation should mean under modality uncertainty. We propose RiVaT-Fuse, a reliability-calibrated variational tensor fusion framework that defines fusion as sample-wise latent-state estimation. Rather than producing a fused vector by direct aggregation, RiVaT-Fuse

Read original source ↗ Open in workspace

recordType

paper

region

Global