NVIDIA Explains Omni-Models: Unified Architecture for Text, Images, Audio, Video, and Actions

NVIDIA Developer · youtube · 2026-08-21

Ming-Yu Liu, VP of Cosmos Lab at NVIDIA, explains the concept of "Omni-Models". These models utilize a unified architecture capable of processing and understanding multiple modalities including text, images, audio, video, and actions.

Original post →

More from Models

Models channel →