Xueyao Zhang

Results 37 comments of Xueyao Zhang

@josephwong14wkh Thank you for raising such good questions! ## New Idea of Vevo1.5 for Information Bottleneck During the development of Vevo1.5, we refined the concept of Vevo's information bottleneck. Specifically,...

> Can I say that Vevo1.5 does not support using audio alone as AR input? As I don't see the content tokenizer for the audio is provided. @liu4lin Yes. The...

> [@RMSnow](https://github.com/RMSnow) Thank you for your detailed explanation. Also, may i know why you set `model.coco.codebook_dim = 8` in `contentstyle_fvq16384_12.5hz.json`, which is so small. As i know it is the...

Hi @josephwong14wkh, I think the loss trend is resonable. You can refer to issue #440 to see my training loss curves.

BTW, use black to format the code to pass the format check

Hi @alinrdinn, thanks for your interest! You are right. Now we have not provided the content tokenizer for Vevo1.5. You can see issue #429 for more details.

Hi @davidesalvi, thanks for your interest! Actually we have been developing zero-shot SVC models. But we found its quality is lower than the look-up-table SVC model. We are still improving...