A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples Paper • 2607.29122 • Published 9 days ago • 4
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling Paper • 2607.23909 • Published 13 days ago • 7
DynEval: Holistic Evaluations of T2I Generative Models in the Wild Paper • 2607.11199 • Published 27 days ago • 1
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI Paper • 2607.11562 • Published 27 days ago • 77
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model Paper • 2607.11643 • Published 27 days ago • 45