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
NewsMBZUAI researchers constrain speech decoding to restore Arabic diacritics
NewsAlibaba launches Qwen4-Max multimodal model across six regions
NewsCMU researchers give everyday objects expressive OATs avatars
NewsWorld Labs releases Frameboy preview for real-time Atlas exploration
NewsAdobe expands removal tools across Photoshop, Premiere and Lightroom
NewsMeituan releases LongCat-2.5 weights under MIT license
NewsWorld Labs releases Atlas tools and developer APIs for world generation
NewsMicrosoft and fal add five video models to Foundry in public preview
NewsOpenAI adds native animated GIF creation with Images 2.6
NewsSpotify and Believe sign deal for paid AI remix and covers add-on
NewsHugging Face releases Swift speech and decision model packages
NewsGoogle DeepMind begins Genie 4 preview with native audio
