@mldcmu
As the world's first machine learning academic department, CMU MLD leads the development of Machine Learning by performing leading research, developing and propagating a model academic curriculum for the field, and by helping society benefit from ML.
1/ I'm excited to share recent results from my first collaboration with the amazing @anayebi.bsky.social
and @leokoz8.bsky.social !
We show how autonomous behavior and whole-brain dynamics emerge in embodied agents with intrinsic motivation driven by world models.
If you're attending @cosynemeeting.bsky.social, come check out our NeuroAgents workshop on Tuesday March 17!
Speakers: Omri Barak, Cristina Savin, @lilweb.bsky.social @reecedkeller.bsky.social Caroline Haimerl, Hannah Choi @xaqlab.bsky.social Srini Turaga, Yanan Sui, @trackingskills.bsky.social
👇
1/ As AI agents become increasingly capable, what must *inevitably* emerge inside them?
We prove selection theorems: strong task performance forces world models, belief-like memory and—under task mixtures—persistent variables resembling core primitives associated with emotion.
Looking forward to presenting on "How behavior shapes recurrent circuits across sensory systems and species: from vision to touch" at the University of Chicago Neuroscience and ML workshop on Wednesday! Details below 👇🧵
One thing that’s often underappreciated is that task-optimized models seed neural foundation modeling because they’re so much more efficient to train than only on brain data — the brain data ends up being the cherry on top for fine-tuning.
1/6 Recent discussions (e.g. Rich Sutton on @dwarkesh.bsky.social’s podcast) have highlighted why animals are a better target for intelligence — and why scaling alone isn’t enough.
In my recent @cmurobotics.bsky.social seminar talk, “Using Embodied Agents to Reverse-Engineer Natural Intelligence”,
A new guest post by MLD associate professor Nihar Shah on The Scholarly Kitchen explores how #AI is reshaping science and publishing.
The post calls for hybrid human-AI workflows, domain-specific benchmarks, and stronger standards for reproducibility.
scholarlykitchen.sspnet.org/2025/09/19/g...
Our first NeuroAgent! 🐟🧠
Excited to share new work led by the talented @reecedkeller.bsky.social, showing how autonomous behavior and whole-brain dynamics emerge naturally from intrinsic curiosity grounded in world models and memory.
Check it out here! 👇
MLD professor @anayebi.bsky.social and his team are working to make robots that process touch like human brains.
#robots #CMU #ML #brain #cortex #SSL
As a long-time fan of Paul Middlebrooks' "Brain Inspired" podcast, it was an honor to be invited on to talk about NeuroAgents, our update to the Turing Test, and AI safety at the end.
Coincidentally recorded on my birthday, no less! Check it out here 👇
Paper: arxiv.org/abs/2502.16238
Implementation (to run on your own models & data!):
What should count as a good model of intelligence?
AI is advancing rapidly, but how do we know if it captures intelligence in a scientifically meaningful way?
We propose the *NeuroAI Turing Test*—a benchmark that evaluates models based on both behavior and internal representations.
