LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces Paper • 2503.01894 • Published 15 days ago • 2
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks Paper • 2412.04626 • Published Dec 5, 2024 • 14
Improving Text-to-Image Consistency via Automatic Prompt Optimization Paper • 2403.17804 • Published Mar 26, 2024 • 18
Measuring Progress in Fine-grained Vision-and-Language Understanding Paper • 2305.07558 • Published May 12, 2023 • 1
