AI Briefing#discrete-diffusion
The latest AI and developer news about #discrete-diffusion, with the original source and a short summary.
The latest AI and developer news about #discrete-diffusion, with the original source and a short summary.
The study presents the first tri-modal Masked Diffusion Models pretrained on text, image-text, and audio-text data, achieving strong results at 3B scale.
DiffusionGemma accelerates text generation by iteratively refining 256 tokens in parallel.