World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 事件

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation arXiv:2604.24764v4 Announce Type: replace Abstract: Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high computational costs and limit scalability. We propose World-R1, a framework that aligns video generation with 3D constraints through reinforcement lea