Embodied AI TopConf · RSS2025

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

RSS2025 / General

世界模型策略学习Benchmark/数据集视频数据
新标签打开 AlphaXiv新标签打开 Project
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets figure
AlphaXiv 中文论文页面（可滚动查看）