Tweeted By @soumithchintala
Really nice update.
— Soumith Chintala (@soumithchintala) May 7, 2020
With a semi-automated ML pipeline that extracts results and tables from papers, they're able to scale much faster.
They released the code and paper to extract results from papers, at: https://t.co/l7caAau4RK and https://t.co/XKHCTwjadK https://t.co/pnvPKmwCqY