MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published 14 days ago • 100
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published 14 days ago • 48
CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions Paper • 2603.26174 • Published 27 days ago • 5