3 papers
cs.LG2026
Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
Li Ju, Mayank Nautiyal, Andreas Hellander +2
Vision-Language Models (VLMs) are typically deterministic in nature and lack intrinsic mechanisms to quantify epistemic uncertainty, which reflects the model's lack of knowledge or…
cs.LG2026
GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
Mayank Nautiyal, Li Ju, Andreas Hellander +2
Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through normalization typically expose neither \…
cs.LG2025
Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
Li Ju, Max Andersson, Stina Fredriksson +4
Vision-language models (VLMs) as foundation models have significantly enhanced performance across a wide range of visual and textual tasks, without requiring large-scale training f…