Member-only story
2022–11–15 | Your Daily AI Research tl;dr 🧠
More layoffs, Latent-NeRF, and faster text-to-image models…
2 min readNov 15, 2022
Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.
1️⃣ Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces
A novel text-to-image model requiring less than 10 steps to sample high-fidelity images, using a speed-optimized architecture allowing to sample a single image in less than 500 ms, while having 573M parameters.
Link to the paper: https://arxiv.org/pdf/2211.07292.pdf
2️⃣ Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
An efficient NeRF approach based on Latent Diffusion Models.
Link to the paper: https://arxiv.org/pdf/2211.07600.pdf
