From Zero to Hero: Training-Free Custom Concept Spawning in World Models
- Published
- Source
- arXiv
- Paper number
- 289
- Field
- Computer Vision
- arXiv ID
- 2606.02575
Key points
- The paper introduces a training-free method for concept spawning called SPAWN, which stands for Swapping Pinned Anchor with Windowed iNjection.
- SPAWN exploits a structural property of image-to-video backbones: the first slot in context memory is pinned to the reference frame and serves as the anchor for every generated chunk.
- Experiments show that SPAWN integrates concepts with consistent lighting, scale, and perspective while preserving identity and temporal consistency, demonstrating that controllable concept spawning is possible in existing autoregressive world models without any training.
Paper links
External research summaries. These are not HDATF publications or measured product results.