minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
- Published
- Source
- arXiv
- Paper number
- 270
- Field
- Computer Vision
- arXiv ID
- 2605.30263
Key points
- Training stage: Camera controllability does not appear immediately. With the HY1.5 backbone, the model showed no responsiveness at 2,000 steps, began showing signs of control at 5,000 steps, and stabilized only after 8,000 steps.
- Embodied AI: It gives robots a mental simulator that predicts the visual consequences of their actions.
- Game development: It generates infinite, interactive environments that respond instantly to player movement.
Paper links
External research summaries. These are not HDATF publications or measured product results.