I did a quick check with revin to see if it is causal along the sequence length axis, where by "causal" I mean that only the past and current tokens are used for transforming the token (or in other words that the future tokens cannot impact past). My results show that RevIN is not causal.
Thank you for the code.
I did a quick check with revin to see if it is causal along the sequence length axis, where by "causal" I mean that only the past and current tokens are used for transforming the token (or in other words that the future tokens cannot impact past). My results show that RevIN is not causal.
Can you confirm that this is correct? Thanks!