collaborators

5 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 \…

stat.ML2026

OneFlowSBI: One Model, Many Queries for Simulation-Based Inference

Mayank Nautiyal, Li Ju, Melker Ernfors +5

We introduce \textit{OneFlowSBI}, a unified framework for simulation-based inference that learns a single flow-matching generative model over the joint distribution of parameters a…

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…

cs.CV2025

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…