TwelveLabs Launches Marengo 3.0 on Amazon Bedrock
New multimodal model analyzes video as a temporal stream, reducing storage costs by 50%.
Video understanding company TwelveLabs released Marengo 3.0, making the model available directly through Amazon Bedrock. The new foundation model represents a technical shift in how AI processes video content, treating it as a continuous temporal stream rather than a sequence of static images.
Native Video Understanding
Marengo 3.0 is designed to solve the "dark data" problem of enterprise video archives. - Temporal Reasoning: The model can understand cause and effect, track specific entities (like a player in a sports game) across time, and comprehend actions in context. - Efficiency: TwelveLabs claims the model offers a 50% reduction in storage …
Archive Access
This article is older than 24 hours. Create a free account to access our 7-day archive.