5 papers
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 \…
OneFlowSBI: One Model, Many Queries for Simulation-Based Inference
Mayank Nautiyal, Li Ju, Melker Ernfors +5
Simulation-based inference (SBI) methods typically amortize a single query, usually the posterior, so each further conditional or marginal needs its own model. Existing generalists…
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…
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…
PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models
Mayank Nautiyal, Stela Arranz Gheorghe, Kristiana Stefa +3
Language-guided attention frameworks have significantly enhanced both interpretability and performance in image classification; however, the reliance on deterministic embeddings fr…