Alibaba's Qwen team has introduced Qwen-MM-Plugins, a new framework designed to enhance agent capabilities with multimodal functionalities. This system allows agents to process and interact with various data formats including images, videos, and documents, and can even perform tasks like video editing and working with 3D/CAD models. The development marks a progression from multimodal models to fully multimodal agents. AI
IMPACT Enhances agent capabilities by enabling interaction with diverse data types like images, videos, and 3D models.
RANK_REASON Product release from a major AI lab, but not a core model release.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
