UnmuteUnmuteAI at MetaX (Twitter)We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative…Open video page1.4KLike on XShareXOpen on X (Twitter)
AI at MetaX (Twitter)Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for…Open video page3.4KLike on XShareXOpen on X (Twitter)
AI at MetaX (Twitter)🏆 We're thrilled to announce that Meta FAIR’s Brain & AI team won 1st place at the prestigious…Open video page2.8KLike on XShareXOpen on X (Twitter)
AI at MetaX (Twitter)Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model…Open video page6.5KLike on XShareXOpen on X (Twitter)
AI at MetaX (Twitter)Introducing Muse Image and Muse Video, the first media generation models developed by Meta…Open video page2.5KLike on XShareXOpen on X (Twitter)
Alexandr WangX (Twitter)4/ to achieve maximum memory efficiency, we quantize model weights to ~4-bit, getting the language…Open video page497Like on XShareXOpen on X (Twitter)
Stability AIX (Twitter)Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video…Open video page3.2KLike on XShareXOpen on X (Twitter)
Jordan EldredgeX (Twitter)If I wanted to give a talk about getting Modern Winamp skins to run in the browser what would be a…Open video page551Like on XShareXOpen on X (Twitter)
Cohere LabsX (Twitter)Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and visionOpen video page456Like on XShareXOpen on X (Twitter)
Xihui LiuX (Twitter)Introducing Moto: Latent Motion Token as the Bridging Language for Robot Manipulation.Open video page106Like on XShareXOpen on X (Twitter)
Artsiom SanakoyeuX (Twitter)We have released the code and weights for our #CVPR2023 paper "Avatars Grow Legs: Generating Smooth…Open video page300Like on XShareXOpen on X (Twitter)
Amil DravidX (Twitter)The latent space of earlier generative models like GANS can linearly encode concepts of the data.Open video page183Like on XShareXOpen on X (Twitter)
Tom YehX (Twitter)Transformer by hand✍️ Excel ~ I designed this exercise to show the core math of a Transformer model…Open video page1.1KLike on XShareXOpen on X (Twitter)
Stability AIX (Twitter)We are pleased to announce the availability of Stable Video 4D, our very first video-to-video…Open video page1.1KLike on XShareXOpen on X (Twitter)
Mihir PrabhudesaiX (Twitter)1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter…Open video page722Like on XShareXOpen on X (Twitter)
Yi ZhouX (Twitter)Coarse2Real (C2R) transfers simple 3D renderings into realistic style video.Open video page183Like on XShareXOpen on X (Twitter)
Nathan C. FreyX (Twitter)With this model release, Claude is beginning to feel like a very capable assistant for research.Open video page126Like on XShareXOpen on X (Twitter)
Ettore Di GiacintoX (Twitter)parakeet.cpp: native C++/ggml (ggml) inference for NVIDIA AI Developer's Parakeet, one of the best…Open video page368Like on XShareXOpen on X (Twitter)
Physical IntelligenceX (Twitter)Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and…Open video page1.3KLike on XShareXOpen on X (Twitter)