Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 12 days ago • 84
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating Paper • 2606.21661 • Published Jun 19 • 28
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models Paper • 2606.26694 • Published 27 days ago • 15