Sign in

CMU MLD

@mldcmu.bsky.social
21 followers 5 following 6 posts

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.

PostsRepliesMedia
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 30/09/2026
Proud to announce our benchmark ROGUE was awarded a 2026 Corrigibility Prize by the Corrigibility Research Fund! www.lesswrong.com/posts/3uJqhr...
lesswrong.com
Corrigibility Prizes for Existing Work — LessWrong
One of my goals for the Corrigibility Research Fund is to retroactively encourage high-quality research on AI alignment (and corrigibility in particu…
121
Reposted by CMU MLD
CMU Griffin School of Computer Science @scsatcmu.bsky.social · 30/09/2026
A landmark $500 million gift will transform Carnegie Mellon University’s top-ranked School of Computer Science into a global powerhouse shaping students, research and technologies to address emerging global challenges.
cmu.edu
$500M Gift Will Fuel Next Era of Computer Science at Carnegie Mellon
A landmark $500 million gift will transform Carnegie Mellon University’s top-ranked School of Computer Science into a global powerhouse shaping students, research and technologies to address emerging ...
177
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 21/09/2026
Check out the CMU SCS podcast episode highlighting our lab's work on reverse-engineering natural intelligence with autonomous agents: www.youtube.com/watch?v=-U7S...
youtube.com
Very Much Inspired By the Nervous System
YouTube video by GeekWire
051
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 14/09/2026
If you're interested in the discussions around the merits of NeuroAI for understanding the mind & brain, check out our #CCN2026 GAC Debate recording! www.youtube.com/watch?v=kYES...
youtube.com
CCN 2026 | GAC: NeuroAI Methods & Frameworks
YouTube video by Cognitive Computational Neuroscience
1173
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 11/09/2026
CMU is hiring an Assistant Professor in NeuroAI! Come join our awesome NeuroAI community 🧠🤖: apply.interfolio.com/189268
apply.interfolio.com
Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio
02811
Reposted by CMU MLD
TTIC @tticconnect.bsky.social · 25/08/2026
1/5 The growing gap between AI/ML theory and practice. "Current AI is used to learn much more complex tasks than even a couple of months ago," said Maria-Florina (Nina) Balcan of @csdatcmu.bsky.social, at TTIC's Learning-driven Algorithms and Machine-aided Proofs Workshop
101
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 17/08/2026
If you are attending @UncertaintyInAI #UAI2026 in Amsterdam, I will be presenting this work on "What Capable Agents Must Know" tomorrow (Tuesday) in the poster session as Poster #205! Poster below 👇 if you can't make it: anayebi.github.io/files/poster...
071
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 04/08/2026
Version 2 of Theory of Contravariance w/ @dyamins.bsky.social is out! New material on contravariance for Transformers, and the theory of Representational Similarity Analysis (RSA) and centered kernel analysis (CKA)/Procrustes.
3155
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 31/07/2026
Now accepted to the AI, Ethics, and Society 2026 conf under the new title: "When Do AI Gains Become Broadly Shareable?" With all the rapid progress in AI, it is critical to now rigorously characterize the institutional conditions that allow gains from greater AI capability to be broadly shared.
141
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 22/07/2026
The blogpost exposition on our "zippering theorems" in Section 4 from our recent Contravariance Theory paper is now out! These zippering theorems explain why end-to-end optimization for downstream tasks often seems to strongly constrain upstream representations.
141
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 13/07/2026
1/6 Why have deep neural networks aligned so strongly with brains for the past 15 years? What explains it? @dyamins.bsky.social & I make progress on this question in our new paper👇 In a nutshell, we *prove* that for sufficiently hard tasks, the choice of alignment metric does *not* matter.
2317
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 04/07/2026
In case you want to learn more about AI safety this 4th, check out the recent recording of some of my group's work on the AI Safety Research directory! www.youtube.com/watch?v=XWQJ...
youtube.com
Corrigibility and the ROGUE Benchmark with Prof. Nayebi, NeuroAgents Lab
YouTube video by AI Safety Research Directory
131
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 28/06/2026
Check out my friend Scott Aaronson's latest blogpost for his recollections of the Aumann conference! scottaaronson.blog?p=9875
scottaaronson.blog
50 Years of Aumann’s Agreement Theorem
One of the most popular posts in this blog’s history was Common Knowledge and Aumann’s Agreement Theorem, based on a lecture that I gave to high-school students 11 years ago. One of the…
121
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 23/06/2026
How did Aumann's agreement theorem come to be? I've uploaded the full video👇from Nobel laureate Bob Aumann's 96th birthday conference in Paris, celebrating 50 years of “Agreeing to Disagree.” At 1:11:09, I ask Aumann about meeting von Neumann & Morgenstern, their influence on his career,
131
CMU MLD @mldcmu.bsky.social · 22/06/2026
👀Watch @anayebi.bsky.social's AAAI 26 talk on the first formal guarantees on corrigibility and the limits of safety filters.
010
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 02/06/2026
Now accepted to #UAI2026 (@auai.org)! Check out v2 of the paper on arXiv with explicit world model recovery algorithms under partial observability in Theorems 3-4. See you in Amsterdam in August!
171
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 29/05/2026
Wow! This is a *must-watch* for anybody interested in modern AI today and where it's going, with talks from rockstars—that include 3 Turing Award winners (Dana Scott being the 4th in attendance!)—on topics such as: AI safety (Ron Rivest), using AI in research and improving reliability (Les Valiant👇
131
CMU MLD @mldcmu.bsky.social · 29/05/2026
At Simons Institute for the Theory of Computing: The Role of TCS in Modern Machine Learning, a workshop on the interplay of theory and AI. Co-organized by MLD professor Nina Balcan and featuring Professor Tom Mitchell among many other field-defining scientists. simons.berkeley.edu/workshops/ro...
simons.berkeley.edu
The Role of TCS in Modern Machine Learning
This 4-day workshop will mark the journey of learning theory from the fringes of TCS to a core topic distinguished by its many mutually rewarding interactions with other areas. It will highlight recen...
030
CMU MLD @mldcmu.bsky.social · 17/03/2026
MLD Professor Maria-Florina Balcan will be the featured speaker at TTIC's Distinguished Lecture Series on Monday March 23. She'll speak on "Theory for modern AI: learning theoretic, game theoretic, and algorithmic perspectives."
031
Reposted by CMU MLD
Deying Song @deyingsong.bsky.social · 01/01/2026
I’m happy to share that one of my PhD works, Neuronal heterogeneity of normalization strength in a circuit model, is published in Science Advances (www.science.org/doi/10.1126/...). 🧵1/n
science.org
Neuronal heterogeneity of normalization strength in a circuit model
Diverse inhibitory currents generate heterogeneous normalization that enhances visual stimulus encoding.
122
Reposted by CMU MLD
Reece Keller @reecedkeller.bsky.social · 05/06/2025
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.
212527
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 05/03/2026
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 👇
0113
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 04/03/2026
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.
1185
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 23/02/2026
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 👇🧵
1164
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 12/02/2026
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.
261
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 29/09/2025
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”,
1104
CMU MLD @mldcmu.bsky.social · 24/09/2025
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...
scholarlykitchen.sspnet.org
Guest Post — May the AI Be With Science - The Scholarly Kitchen
AI has opened a new chapter in the saga of science and peer review. Today, guest author Prof. Nihar B. Shah explains how, if guided with integrity, AI can open galaxies of possibilities.
000
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 05/06/2025
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! 👇
2246
CMU MLD @mldcmu.bsky.social · 10/06/2025
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
000
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 09/04/2025
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 👇
183
Reposted by CMU MLD
Aran Nayebi @anayebi.bsky.social · 25/02/2025
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.
33913