Kilian

I have added torch backend to the list. I agree that it should be one of the next 'big' module to create (balanced & unbalanced solvers). I know @rflamary has...

I think it is best to refuse most PRs while we have not finished the major changes. It might take several months, but once it is done, it will be...

I reedited my first post with the name shifting for both documentation and code.

Hello @ngayraud, No one has worked on the domain adaptation module yet. If you want, you can work on it :). But I think it is best to wait to...

Hello all, I agree :) I have completed the PR on the stochastic module.

We should give credit to stochastic interpolants and rectified flows at the beginning of the notebook. Basically saying that all 3 methods are similar and concurrent ICLR2023 papers

Hi, Thank you! I will correct that shortly.

Oh that’s indeed a typo… I changed the name of the function last minute and forgot to change this. You are right! The correct function is `sample_conditional_pt`. Edit: I have...

Hello, This seems to be a problem with Torchdyn. A workaround might be to use torchdiffeq instead. You could also write your own custom Euler integration method. Unfortunately, as the...

Hello, Thank you for noticing this unused variable. This will be removed in a future PR. Regarding the `generate_cifar10.py`, I agree it is a good idea. I will add it...