Stable Diffusion

AbstractText-to-image generative models have achieved unprecedented success in generating high-quality images based on natural language descriptions. However, it is shown that these models tend to favor specific social groups when …...

AbstractAutomatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with text references. This differs from human language processing, for which visual imagination often improves comprehension. …...

AbstractThis paper describes the participation of the RCLN team at the Visual Word Sense Disambiguation task at SemEval 2023. The participation was focused on the use of CLIP as a …...