This site is currently broken for new queries. It seems like some bot hit it and we ran out of exa credits.
Enter your personal website to find others like you. Powered by Exa's "find similar". Built on Val Town.
We started it as just a fun way to talk to people during the height of COVID, and we've been amazed and humbled by the uptake.
Language models are multilingual chain-of-thought reasoners.
understanding the memorization phenomenon and building tools to mitigate undesirable consequences of this.
81 out of 320 submissions are accepted.
I also worked with
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
He's the force of nature behind the widely used Flash Attention (usage).
SummerTime: Text Summarization Toolkit for Non-experts
Introduce SpecAugment, which is a simple data augmentation method for speech recognition.