Mark Saroufim    @marksaroufim    11/25/2021      

This README was the best visual explanation of gradient checkpointing I’ve seen Made it click for me. Hopefully someone else finds it useful too.
    5         35


Stephan Hoyer    @shoyer    11/24/2021      

Gradient checkpointing (aka rematerialization) is an easy trick that can save massive amounts of memory for calculating gradients. If you differentiate through computation involving long iterative processes (like ODE solving), learn it and make it part of your toolkit! 👇🧵
    2         3

Christian Wolf    @chriswolfvision    11/25/2021      

I am happy that my reviews have been useful to the BMVC ACs...

Sam Altman    @sama    12/4/2021      

Goal for today is to design it (in public) and either decide not to do it or find someone to run a small "beta"--I have time to work on it today but not to actually work on it. Or someone can just take the idea and do whatever they want with it!

AK    @ak92501    11/25/2021      

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion abs: presents a unified multimodal pretrained model that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks
    1         1