Your Daily AI Research tl;dr — 2022–10–04 🧠

Visual Prompt Tuning for Generative Transfer Learning, A Benchmark for Few-Shot Region-Aware Machine Translation and Activeloop releases Deep Lake, the data lake for deep learning!

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 Visual Prompt Tuning for Generative Transfer Learning

A recipe for learning vision transformers (on image synthesis) by generative knowledge transfer using prompt tuning to adapt to new domains.

Link to the paper: https://arxiv.org/pdf/2210.00990.pdf

2️⃣ FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation

A new dataset and evaluation benchmark for Few-shot Regionaware Machine Translation, a type of style-targeted translation.

“The dataset consists of professional translations from English into two regional variants each of Portuguese and Mandarin Chinese.”