COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation Paper • 2502.02589 • Published 7 days ago • 8
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step Paper • 2501.13926 • Published 19 days ago • 34
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching Paper • 2412.15205 • Published Dec 19, 2024
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens Paper • 2501.07730 • Published 29 days ago • 16