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
PapersUDE: A Unified Driving Engine for Human Motion Generation
PapersRANA: Relightable Articulated Neural Avatars
PapersULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On
PapersDiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
PaperseDiffi: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers
PapersMusika! Fast Infinite Waveform Music Generation
NewsCALA uses DALL-E to generate designs for clothing, accessories, footwear, and lifestyle products
PapersAutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling
PapersHigh Fidelity Neural Audio Compression
NewsShutterstock to integrate OpenAI’s DALL-E 2 and launch fund for contributor artists
PapersPrompt-to-Prompt Image Editing with Cross-Attention Control
PapersLION: Latent point diffusion models for generating 3D shapes