1 citations · 2 across the 14 of their papers we have counts for
Showing 2026 · cs.CVShow all
2 papers · 2 filters
cs.CV2026
Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders
Sergio Lanza, Jae Hee Lee, Stefan Wermter
Vision Language Models (VLMs) have demonstrated impressive performance in tasks requiring joint understanding of images and text, such as image captioning and Visual Question Answe…
cs.CV2026
Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions
Thomas Vitry, Kieran Edgeworth, Stefan Wermter +1
Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches to bias mitigation and analy…