RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 5 days ago • 99
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Paper • 2604.10949 • Published 5 days ago • 38
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published 16 days ago • 479
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published 9 days ago • 114
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published 23 days ago • 154
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? Paper • 2603.03241 • Published Mar 3 • 87
