The upside of this hopefully is pretty well established. There's a couple interesting little wrinkles in the in the paper particularly around the stride of inference where there seems to be some sort of performance penalty associated with the boundaries between the patches and so you have an interesting strategy for overcoming that but then i've also seen most of the commentary on this paper online has been like effusively positive and really hyping it up. no way we we can compare so we have to convert our results to word level of publicity yes.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode