The paper fixes a big problem in long video generation: models either forget what happened or slowly drift off-topic over time.
VideoAR is a new way to make videos with AI that writes each frame like a story, one step at a time, while painting details from coarse to fine.
SpaceTimePilot is a video AI that lets you steer both where the camera goes (space) and how the action plays (time) from one input video.
The paper teaches a video model to squeeze long video history into a tiny memory while still keeping sharp details in single frames.
AniX is a system that lets you place any character into any 3D world and control them with plain language, like “run forward” or “play a guitar.”