3 papers
cs.CV2026
Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed
Xinnuo Xu, Anja Thieme, Daniela Massiceti +6
State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users. Our emp…
cs.CV2024
Understanding Information Storage and Transfer in Multi-modal Large Language Models
Samyadeep Basu, Martin Grayson, Cecily Morrison +3
Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these me…
cs.CV2023
Explaining CLIP's performance disparities on data from blind/low vision users
Daniela Massiceti, Camilla Longden, Agnieszka Słowik +3
Large multi-modal models (LMMs) hold the potential to usher in a new era of automated visual assistance for people who are blind or low vision (BLV). Yet, these models have not bee…