2022-11-18 | Your Daily AI Research tl;dr ??

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.

Receive your daily update right in your inbox ??

1?? ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

ImageNet-X–a set of sixteen human annotations of factors such as pose, background, or lighting for the entire ImageNet-1k validation set as well as a random subset of 12k training images.

Link to the paper: https://arxiv.org/abs/2211.01866

Code/Dataset

2?? Toward a realistic model of speech processing in the brain with self-supervised learning

"We compare a recent self-supervised architecture, Wav2Vec 2.0, to the brain activity of 412 English, French, and Mandarin individuals recorded with functional Magnetic Resonance Imaging (fMRI), while they listened to ≈ 1 h of audio books." *really interesting paper and results!!*

Link to the paper: https://arxiv.org/abs/2206.01685

Join the discussion with fellow AI enthusiasts

?? The State of Multilingual AI

Are you wondering what is the state of multilingual AI? Have a look at this great blog post by Sebastian Ruder! He covers the recent contributions`, "how much" multilingual really are these models.

Please subscribe and share the newsletter with your AI techy friends if it was helpful and join our 4'000+ readers. 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