Member-only story
Your Daily AI Research tl;dr — 2022–08–18 🧠
An Open-Source image generator AI model, Riemannian Diffusion Models and Understanding Long Documents…
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 Riemannian Diffusion Models
“In this work, we generalize continuous-time diffusion models to arbitrary Riemannian manifolds and derive a variational framework for likelihood estimation.”
Link to the paper: https://arxiv.org/pdf/2208.07949.pdf
2️⃣ Understanding Long Documents with Different Position-Aware Attentions
In this paper, the authors tackle the problem that comes with long documents (large text inputs) trying “different approaches in handling 1D and new 2D position-aware attention with essentially shortened context.”
Link to the paper: https://arxiv.org/pdf/2208.08201.pdf
Join the discussion with fellow AI professionals on Discord!
