
StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.

An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments

An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments

Enable smooth global interactions in 36 languages.

Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances.


Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation.

Enable smooth global interactions in 36 languages.

Predicts the 3D structure of a protein from its amino acid sequence.

Predicts the 3D structure of a protein from its amino acid sequence.


Verify compatibility of OpenUSD assets with instant RTX render and rule-based validation.