89 citations · 128 across the 12 of their papers we have counts for
3 papers · 1 filter
Generative Text Modelling and Language-Guided Visual Attention for Deciphering Palimpsests
Robin Hollifeldt, Tianru Zhang, Jessica Ström +1
Recovering obscured text in palimpsests, i.e. the manuscripts where the original writing (under-text) was erased and overwritten for reuse, is vital for preserving lost information…
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 \…
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…