SM
Sparse Models
Indexing
Sifting through hundreds of thousands of hours of indexed videos
Sparse Models
Sifting through hundreds of thousands of hours of indexed videos
Sparse Models
2
Mentions
77.5K
Views
“Models where only a small portion of parameters are activated for any given prediction (e.g., Mixture-of-Experts); major improvement in compute efficiency; Gemini models are sparse.”
“developed a way to make sparse models essentially having a very large capacity model but now instead of activating the entire model on every token or every example you can activate just a small portio...”
Arcmira media summary
Arcmira tracks where Sparse Models is discussed across indexed YouTube videos, transcripts, channels, and related entities.
Models where only a small portion of parameters are activated for any given prediction (e.g., Mixture-of-Experts); major improvement in compute efficiency; Gemini models are sparse.
developed a way to make sparse models essentially having a very large capacity model but now instead of activating the entire model on every token or every example you can activate just a small portion of it.
Arcmira tracks 2 indexed media appearances or mentions for Sparse Models, tied to source videos, channels, and transcript-derived context.
Arcmira uses indexed YouTube videos and transcripts. Representative source evidence on this page includes "Stanford AI Club: Jeff Dean on Important AI Trends" with transcript-derived context and links when available.
Sparse Models is connected to Google, Google DeepMind, Ironwood in Arcmira's media graph.