AI Agent Skills

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"