News for hackers. Stuff that matters.
Re:VideoPoet A large language model for zero-shot video gene... by omneity on Wednesday December 20, 2023 @05:08AM (#38707058)
That would mean most likely that the video is the result of a prompt without any example.

Illustrated examples from how Google does it here: https://blog.research.google/2023/11/zero-shot-adaptive-prom...

EDIT: corrected answer factuality.

Re:VideoPoet A large language model for zero-shot video gene... by stevage on Wednesday December 20, 2023 @05:14AM (#38707083)
I wonder why "zero-shot" rather than "one-shot".
Re:VideoPoet A large language model for zero-shot video gene... by omneity on Wednesday December 20, 2023 @07:03AM (#38707692)
I was wrong indeed, this is technically called zero-shot prompting.

Zero-shot prompting here means without an example, i.e. "show me a panda on a skate". The opposite would be few-shot prompting, "write me a limerick like these 5 examples".

Re:VideoPoet A large language model for zero-shot video gene... by hyperparticles on Wednesday December 20, 2023 @10:29AM (#38709718)
In addition, there are some tasks that the model can do and was never trained on, see the newly added paper link in the website.