Seeing is Believing with MIT’s Ziming Liu

Ziming Liu discusses Brain-Inspired Modular Training (BIMT) for neural networks, enhancing modularity and interpretability in AI and physics research.


Watch Episode Here

Video Description

Ziming Liu is a Physics PhD student at MIT and IAIFI, advised by Prof. Max Tegmark. Ziming’s research is at the intersection of AI and physics. Today’s discussion goes in-depth on Liu’s paper “Seeing is Believing” where he presents Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. The ability to see modules visually can complement current mechanistic interpretability strategies.

The Cognitive Revolution is a part of the Turpentine podcast network. To learn more:

Seeing is Believing, authors: Ziming Liu, Eric Gan, and Max Tegmark

Ziming Lu:

(00:00) Episode preview
(01:16) Nathan introduces Ziming Liu and his research
(04:50) What motivated Ziming's research into neural networks and modularity
(08:06) Key Visuals of "Seeing is Believing"
(08:44) Biology analogy & paper overview
(15:07) Sponsor: Omneky
(26:08) Research precedents
(30:00) Locality vs modularity
(37:40) Shoutout Tiny Stories -
(39:00) Quantization Model of Neuro Scaling.
(1:00:00) How this work can impact mechanistic interpretability strategies
(1:27:00) Training
(1:46:30) Downscaling large scale models

Thank you Omneky ( for sponsoring The Cognitive Revolution. Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work, customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off.


Great! You’ve successfully signed up.

Welcome back! You've successfully signed in.

You've successfully subscribed to The Cognitive Revolution.

Success! Check your email for magic link to sign-in.

Success! Your billing info has been updated.

Your billing was not updated.