SHIFT: Vision-Language Models for Accessible CH Fine-tuned multimodal LLMs auto-generates rich cultural-heritage descriptions for visually impaired audiences in Romanian, Serbian and German. JoseferEins/ArtQwen-Curator-DE Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-RO Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-SR Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-ML Image-to-Text • Updated Sep 2, 2025
SHIFT: Vision-Language Models for Accessible CH Fine-tuned multimodal LLMs auto-generates rich cultural-heritage descriptions for visually impaired audiences in Romanian, Serbian and German. JoseferEins/ArtQwen-Curator-DE Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-RO Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-SR Image-to-Text • Updated Sep 2, 2025 JoseferEins/ArtQwen-Curator-ML Image-to-Text • Updated Sep 2, 2025
