Member-only story
Your Daily AI Research tl;dr — 2022–08–17 🧠
An Efficient Framework for Knowledge Transfer, 3D reconstruction and meet with me in Las Vegas this week!
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 PlaneFormers: From Sparse View Planes to 3D Reconstruction
A transformer applied to 3D-aware plane tokens to perform 3D reasoning (produce plane correspondences and refined cameras using).
Link to the paper: https://arxiv.org/abs/2208.04307
2️⃣ Teacher Guided Training: An Efficient Framework for Knowledge Transfer
“We propose the teacher-guided training (TGT) framework for training a high-quality compact model that leverages the knowledge acquired by pretrained generative models, while obviating the need to go through a large volume of data.”
Link to the paper: https://arxiv.org/abs/2208.06825