Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
SynCo: Learning Cross-Modal Synergy by Contrasting Interaction Residuals
Yavuz Yarici, Ghassan AlRegib
Multimodal contrastive learning is a dominant paradigm for learning transferable representations from unlabeled data, but standard objectives primarily capture information that is…
cs.CV2026
RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty
William Stevens, Mohit Prabhushankar, Ghassan AlRegib
Epistemic uncertainty estimation is essential for identifying regions where deep learning system outputs may be unreliable. However, existing approaches require computationally exp…