Multimodal AI
Multimodal AI systems work with more than one kind of input or output, such as text, images, audio, or video.
Follow model and application developments in speech, image, and video. Coverage looks at generation, understanding, media formats, and practical developer access.
Latest coverage
Articles
NewsFacebook introduces AI Sandbox
NewsTurn Text into Music
NewsDeepFloyd IF, a powerful text-to-image model that can smartly integrate text into images
NewsAdobe introduces Firefly, a family of new creative generative AI
PapersS-NeRF: Neural Radiance Fields for Street Views
NewsThe new Bing comes with Bing Image Creator
PapersUniversal Guidance for Diffusion Models
NewsThe long-awaited release of multimodal GPT-4 will take place next week
Newschat.D-ID enables anyone to talk face to face with AI
Papers3D Generation on ImageNet
Papers3D-aware Conditional Image Synthesis
PapersSinMDM: Single Motion Diffusion