HKUDS, a team at the University of Hong Kong, has released VideoAgent, an open-source agent framework that automates video understanding, editing and generation from a single natural-language instruction, publishing it on GitHub. Formally titled VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking, it is built around assembling video tasks as agent-driven workflows.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.