Your Daily AI Research tl;dr 2022-07-11 ??

Welcome to your official daily AI research tl;dr (often with code and news) for AI enthusiasts 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. I will also take this opportunity to share daily exciting news in the field.

Let's get started with this iteration!

1?? Beyond neural scaling laws: beating power law scaling via data pruning?

They "show how both in theory and practice [they] can break beyond power-law scaling and reduce it to exponential scaling instead if we have access to a high-quality data pruning metric that ranks the order in which training examples should be discarded to achieve any pruned dataset size."

Link to the paper: https://arxiv.org/pdf/2206.14486v1.pdf

2?? LViT: Language meets Vision Transformer in Medical Image Segmentation

One of the main challenges with medical image segmentation is having access to enough high-quality labeled data. In this work, medical text annotation is introduced to compensate for the quality deficiency in image data. The text information can guide the generation of pseudo labels to a certain extent and further guarantee the quality of pseudo labels in semi-supervised learning.?

Link to the paper: https://arxiv.org/pdf/2206.14718v1.pdf

Code and dataset: https://github.com/HUANGLIZI/LViT

?? IBM used Watson to Predict who will Win Wimbledon

You can select a singles match and see an AI-generated preview and the percentage likelihood that each player will win. Cool fun application of artificial intelligence right here.

Try it: https://www.wimbledon.com/en_GB/matchinsights/1701.html

Learn more: https://thenextweb.com/news/inside-wimbledon-ibm-ai-engagement-tennis-fans

And we are already at the end of this iteration!

I hope you liked the format. Please subscribe and share it with your AI techy friends if you've enjoyed it or if it was helpful. Feel free to follow my weekly newsletter where I go in-depth into one of the papers shared, and our newsletter at Towards AI, sharing the most exciting news, papers, articles, and memes weekly.

Thank you for reading,

Louis