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

About this episode

This episode discusses the World-R1 framework for improving 3D constraints in text-to-video generation using reinforcement learning.

🤗 Upvotes: 102 | cs.CV Authors: Weijie Wang, Xiaoxuan He, Youping Gu, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang Title: World-R1: Reinforcing 3D Constraints for Text-to-Video Generation Arxiv: http://arxiv.org/abs/2604.24764v1 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 learning. To facilitate this alignment, we introduce a specialized pure text dataset tailored for world simulation. Utilizing Flow-GRPO, we optimize the model using feedback from pre-trained 3D foundation models and vision-language models to enforce structural coherence without altering the underlying architecture. We further employ a periodic decoupled training strategy to balance rigid geometric consistency with dynamic scene fluidity. Extensive evaluations reveal that our approach significantly enhances 3D…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• 3D constraints
• text-to-video generation
• reinforcement learning
• video foundation models
• geometric consistency
• world simulation

Keywords

• video generation
• 3D consistency
• Flow-GRPO
• structural coherence
• dynamic scene fluidity

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min