Will Berman

> I realize SVD is quite well-known, but it would be useful to mention example models that use SVD, if you are aware of any, as motivation. I'm not aware...

> I found some models using SVD: > > * [SVD-Embedded Deep Autoencoder for MIMO Communications](https://arxiv.org/abs/2111.02359) mentions models with SVD > * [Cloud K-SVD for Image Denoising](https://www.researchgate.net/publication/358344505_Cloud_K-SVD_for_Image_Denoising) no much info...

> @williamberman - Hi, I'm actually not at Schneider Electric anymore (hence the "SE" in my old name), I've switched to Databricks 🥳 . > > So I didn't see...

I put up a draft PR https://github.com/onnx/onnx/pull/4416 I believe the main remaining question is re: SVD differentiability

Hello, super sorry wasn't aware someone was already working on this! I ported the VQVAE for the ITHQ dataset. Would love to help contribute if possible :) I put up...

@345ishaan definitely not over the finish line, just ported the autoencoder for one of the models! Happy to collaborate :)

@cientgu @zzctan Could I have some help parsing q_posterior? https://github.com/microsoft/VQ-Diffusion/blob/3c98e77f721db7c787b76304fa2c96a36c7b00af/image_synthesis/modeling/transformers/diffusion_transformer.py#L235-L267 I believe it's computing equation 11 in log space, but I still have a few questions. I understand it's adapted...

pinged you in discord @345ishaan!

> Wooow - this looks amazing! @patil-suraj mind taking a look here? Thanks! Would love to know if the minimum unit to merge is the completed pipeline or if smaller...

> Hey @williamberman and @345ishaan, > > Sorry for the delay - I have more time going forward and think we can merge this model by next week! > >...