State Space Models for Realtime Multimodal Intelligence: Karan Goel

What are the big breakthroughs required to bring realtime multimodal intelligence to every device in the world? This talk describes the work we're doing at Cartesia on bringing realtime models to life on an entirely new technology stack. I'll describe new research ideas that we developed over the last few years - state space models - that are enabling us to build audio models that are cheaper, faster and higher quality than state of the art approaches.
Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at www.ai.enginee... & join us at the AI Engineer World's Fair in 2025! Get your tickets today at ai.engineer/2025
About Karan
Karan is the Founder / CEO of Cartesia.ai where he builds multimodal models that can be run in real-time on any device. Before founding Cartesia, Karan pursued his PhD from Stanford, where he spent a few years developing the first state space models, building data systems, and researching new methods for robust machine learning. Karan is a recipient of the Siebel Scholarship, graduated from IIT-Delhi and CMU, and is passionate about machine learning, engineering and developer tools.

[@wwkk4964]

Love this

[@ABHISHEKKUMAR-nj7mt]

Snowden started giving talks on ai😅

[@ps3301]

Liquid neural network is the way forward

[@anujfulari6735]

Why don't we model Human Brain biologically?

[@ajithboralugoda8906]

why bother nature already does it!! but we do need to create machines just like any other Automation we have done, is the moot point right

[@anujfulari6735]

@ajithboralugoda8906 Human brain can process realtime data so fast and efficiently. Imagine a machine doing that and just using some Kcal instead of some nuclear source of energy.