RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space Paper • 2606.14700 • Published 20 days ago • 18
DREAM: Where Visual Understanding Meets Text-to-Image Generation Paper • 2603.02667 • Published Mar 3 • 6
Xray-Visual Models: Scaling Vision models on Industry Scale Data Paper • 2602.16918 • Published Feb 18 • 2