Your Daily AI Research tl;dr — 2022–09–16 🧠

Zero-Shot Generalization in Vision-Language Models, 3D Vision with 2D Vision Transformers, and the Top AI Books to Read in 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 Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Test-Time Prompt Tuning (TPT): A method that can learn adaptive prompts on the fly with a single test sample.

Link to the paper: https://arxiv.org/pdf/2209.07511.pdf

2️⃣ Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?

This paper demonstrates the appealing promise to understand the 3D visual world, using a standard 2D ViT architecture, with only minimal customization at the input and output levels without redesigning the pipeline.

Link to the paper: https://arxiv.org/pdf/2209.07026.pdf