Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 4 days ago • 70
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published Jun 11 • 93
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published Apr 13 • 73
Towards Scalable Pre-training of Visual Tokenizers for Generation Paper • 2512.13687 • Published Dec 15, 2025 • 108
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions Paper • 2511.03334 • Published Nov 5, 2025 • 54