Awesome World Models / arXiv

RLVR-World: Training World Models with Reinforcement Learning

作者：作者信息待提取 · 单位：Zhili College, Tsinghua University · 来源：General Approaches to World Models · 发布日期：2025 · 分类：7. Post-training and Inference-Time Scaling for World Models

后训练/规模化基于模型的强化学习
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
RLVR-World: Training World Models with Reinforcement Learning figure
AlphaXiv 中文概览（可滚动查看）