AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
29min chapter
#174 - Odyssey Text-to-Video, Groq LLM Engine, OpenAI Security Issues
Last Week in AI
Advancements in Test Time Learning for RNNs and Data Curation in Multimodal Learning
The chapter covers a research paper introducing a new approach for training models at test time by continuously updating memory with self-supervised training, leading to improved model performance. It also discusses another paper focusing on data curation through joint example selection for multimodal learning, resulting in faster learning and reduced computational usage. Additionally, the chapter explores various papers on optimizing compute spending, addressing literal and non-literal reproduction in language models, and the implications of AI-generated content on copyright concerns.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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