HelloWorld: Enabling Socially Interactive Characters in Video World Models
- Published
- Source
- arXiv
- Paper number
- 828
- Field
- Computer Vision
- arXiv ID
- 2608.05070
Key points
- This is the first video world model to realize social interaction between a character and a user, such as waving, greeting, and speaking to the user.
- The paper proposes a self-distillation pipeline that reuses interaction videos generated by the model itself as training data.
- Without additional training, it controls the timing of interactions at the frame level using only cross-attention masks.
- It builds the first social-interaction benchmark, HelloWorldBench, with 400 samples and 3 interaction metrics.
- It substantially outperforms existing world models on interaction quality while maintaining SOTA-level video aesthetics and camera following.
Paper links
External research summaries. These are not HDATF publications or measured product results.