collaborators
Showing cs.LGShow all

5 papers · 1 filter

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

ConDiSim: Conditional Diffusion Models for Simulation Based Inference

Mayank Nautiyal, Andreas Hellander, Prashant Singh

We present a conditional diffusion model - ConDiSim, for simulation-based inference of complex systems with intractable likelihoods. ConDiSim leverages denoising diffusion probabil…

cs.LG2025

Variational Autoencoders for Efficient Simulation-Based Inference

Mayank Nautiyal, Andrey Shternshis, Andreas Hellander +1

We present a generative modeling approach based on the variational inference framework for likelihood-free simulation-based inference. The method leverages latent variables within…

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…