AI & RoboticsMore in AI & Robotics→
Naver’s Seoul World Model Tries to Fix a Core Weakness in Generative Video
Key Takeaways
- SWM uses 1.2 million Naver Map panoramic images.
- The model generates video from coordinates, camera movement, and text prompts.
- The supplied source says it beat six current video world models on visual quality and temporal consistency.
DE
DT Editorial Team··via the-decoder.com