Google DeepMind brings agentic video understanding to Gemini
Introducing agentic video understanding with Gemini
AI BriefingGoogle DeepMind introduced agentic video understanding for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. The models dynamically scan video clips, reducing token consumption by up to 88% and costs by up to 66% compared with fixed-frame-rate processing, while improving accuracy by up to 7%.
Also reported by 1 other source
- Google DeepMind brings agentic video understanding capabilities to the latest Gemini modelsGoogle DeepMind · September 2
Source: Google DeepMind: Blog · deepmind.google
Event follow-up1
View all event coverage- Google DeepMind brings agentic video understanding to GeminiGoogle DeepMind: Blog · September 2