The model being discussed focuses on analyzing pieces of video and images to make predictions based on the semantic meaning captured in an embedding space, rather than operating on raw pixels. This approach is similar to Sora, as both operate at the level of the embedding space. The goal of the model is to generate meaningful embeddings from video or image patches through an encoder, capturing the essence or meaning of the inputs.

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