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
PapersLEGO-Net: Learning Regular Rearrangements of Objects in Rooms
PapersMEGANE: Morphable Eyeglass and Avatar Network
PapersGLIGEN: Open-Set Grounded Text-to-Image Generation
PapersStyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
PapersHyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
PapersAgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging
PapersZero-Shot Text-Guided Object Generation with Dream Fields
PapersInstantAvatar: Learning Avatars from Monocular Video in 60 Seconds
PapersScalable Diffusion Models with Transformers
PapersNeRF-Art: Text-Driven Neural Radiance Fields Stylization
Papers3DHumanGAN: Towards Photo-realistic 3D-Aware Human Image Generation
PapersNovel View Synthesis with Diffusion Models