PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data Paper โข 2502.14397 โข Published 18 days ago โข 38
WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation Paper โข 2502.08047 โข Published 26 days ago โข 26
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation Paper โข 2502.07870 โข Published 26 days ago โข 43
MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation Paper โข 2502.01572 โข Published Feb 3 โข 20
Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos Paper โข 2501.13826 โข Published Jan 23 โข 24