VideoPoet A large language model for zero-shot video generation

Re:VideoPoet A large language model for zero-shot video gene... by busssard on Wednesday December 20, 2023 @05:58AM (#38707299)

i interpret it that the VideoPoet has not seen the things prompted. One shot means you show it one example of something and it generates equivalents.

However i find it very misleading, as the training data is most likely gigantic. So it is not very accurate calling it zero shot

[ Parent | on HN ]

Re:VideoPoet A large language model for zero-shot video gene... by stevage on Wednesday December 20, 2023 @06:36AM (#38707507)

Ah, thanks, that makes sense.

[ Parent | on HN ]

Re:VideoPoet A large language model for zero-shot video gene... by hyperparticles on Wednesday December 20, 2023 @10:25AM (#38709662)

Author here. We demonstrate zero-shot capability on a few tasks by chaining smaller tasks together. For example, the model was never trained on text-to-audio but we can do it by generating text-to-video followed by video-to-audio.

We just added a link to the paper in the website, you can read more about it.

[ Parent | on HN ]