GFlowNets for generative active learning | Amazon Science

Поделиться
HTML-код
  • Опубликовано: 19 ноя 2024

Комментарии • 7

  • @Mostafa-cv8jc
    @Mostafa-cv8jc 2 года назад

    haha the part about bats had me laugh out loud

  • @DanNavon-b7r
    @DanNavon-b7r 2 года назад

    So cool!

  • @ChocolateMilkCultLeader
    @ChocolateMilkCultLeader 2 года назад

    Great video. Do you guys do collaborations and guest presentations

  • @ramakrishna5480
    @ramakrishna5480 2 года назад

    👍👍👍

  • @paulcurry8383
    @paulcurry8383 2 года назад +2

    I still don’t really get what is new here. It sounds like he is proposing a way to improve generative sampling by modeling a system as a neural network with flow constraints over states?
    I guess I’d like to see a more concrete implementation over something RL struggles with like hand movement to really grasp what he’s proposing. Otherwise it has a similar ring to liquid neural networks, which supposedly have some great mathematical properties but still don’t work in practice.

    • @ThePowerExcess
      @ThePowerExcess 2 года назад

      I love your take on LSMs - even though i love them and I spent like 3 years working on them

    • @maloxi1472
      @maloxi1472 2 года назад

      It's not clear what it is exactly that you're claiming/asking in the first part of your comment.