This paper teaches talking avatars not just to speak, but to look around their scene and handle nearby objects exactly as a text instruction says.
SkyReels-V3 is a single AI model that can make videos in three ways: from reference images, by extending an existing video, and by creating talking avatars from audio.
This paper shows how to turn any normal photo or video into a seamless 360° panorama without needing the camera’s settings like field of view or tilt.
Robots often learn a bad habit called the vision shortcut: they guess the task just by looking, and ignore the words you tell them.
OmniTransfer is a single system that learns from a whole reference video, not just one image, so it can copy how things look (identity and style) and how they move (motion, camera, effects).
TwinBrainVLA is a robot brain with two halves: a frozen generalist that keeps world knowledge safe and a trainable specialist that learns to move precisely.
CoDance is a new way to animate many characters in one picture using just one pose video, even if the picture and the video do not line up perfectly.
FOFPred is a new AI that reads one or two images plus a short instruction like “move the bottle left to right,” and then predicts how every pixel will move in the next moments.
Most text-to-image models act like word-to-pixel copy machines and miss the hidden meaning in our prompts.
NitroGen is a vision-to-action AI that learns to play many video games by watching 40,000 hours of gameplay videos from over 1,000 titles with on-screen controller overlays.
DreamID-V is a new AI method that swaps faces in videos while keeping the body movements, expressions, lighting, and background steady and natural.
GR-Dexter is a full package—new robot hands, a smart AI brain, and lots of carefully mixed data—that lets a two-handed robot follow language instructions to do long, tricky tasks.