video

NVIDIA released Nemotron 3 Nano Omni, a 30B-A3B Mixture-of-Experts model that processes text, images, video, and audio. The model uses a hybrid Mamba-Transformer architecture with 128 experts and achieves 65.8 on OCRBenchV2-En and 72.2 on Video-MME, while delivering up to 9x higher throughput on multimodal tasks compared to alternatives.

OpenAI's ChatGPT has launched its first streaming video service integration, partnering with Tubi. The native app lets users search Tubi's catalog of over 300,000 movies and TV episodes using natural language queries.

A Meta FAIR and New York University research team trained a multimodal AI model from scratch and identified that several widely-held assumptions about multimodal model architecture and training don't align with their empirical findings. The work addresses growing concerns about text data exhaustion in LLM training.