Public KG record
World-Action Model
Recorded overview
A generative model type that denoises future video and a future action.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Capabilities: 联合预测视频和动作
- Capabilities: 同时预测未来视频帧与机器人动作
- Capabilities: 用于机器人控制
- Capabilities: 预测未来视频或世界状态
- Capabilities: 以未来预测引导机器人动作
- Capabilities: 预测未来视频和世界状态，以引导机器人动作
- Supported types: 读取相机帧、机器人状态和文本指令
- Supported types: 输出未来视频帧和动作片段
Evidence coverage
The KG currently records 8 known information dimensions and has 11 undocumented dimensions, linked to 3 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Video-Language Action — alternative to
- Video-Language Action — alternative to
- VLA — competes with
- VLA — competes with
- Dyna-2 — is a