RiVaT-Fuse: Reliability-Calibrated Variational Tensor Fusion for Multimodal Prediction under Modality Uncertainty
RiVaT-Fuse is proposed, a reliability-calibrated variational tensor fusion framework that defines fusion as sample-wise latent-state estimation and achieves the strongest overall predictive rank among direct representation-level baselines while improving probability and label stability under perturbation.
Yin Xu, Tie-Ming Liu, Ye Liang et al.
· 1 citation