6 papers · 1 filter
Squeeze-Release: Iterative Pruning with Exact Structural Minimization
Roman Denkin, Ida Akerholm, Prashant Singh +1
Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We prese…
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…
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 \…
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…
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…
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…