Research lab at @UCSBEngineering revealing the geometric signatures of natural and artificial intelligence | PI: @ninamiolane
Santa Barbara
Joined September 2021
- Tweets1.2K
- Following747
- Followers2.7K
- Likes1.6K
Pinned Tweet
🌟 New review from the lab!
Discover the geometric, topological and algebraic signatures of machine learning and deep learning models.
By @naturecomputes @johmathe @mathildepapillo D. Buracas @hansenlillemark @cashewmake2 @AbbyBertics X. Pennec & @ninamiolane !
In the 20th century, non-Euclidean geometry transformed how we model the world with pen and paper. In this century, it’s revolutionizing how we model the world with machines.
Our review on the topic is out arxiv.org/pdf/2407.09468, led w the brilliant
@naturecomputes @johmathe
Geometric Intelligence Lab retweeted
“To our knowledge, this is the first AI system to pass a professional CAD certification.”
I spent 4 months at Spectral Labs this summer. It was exciting to see a company tackle such interesting and ambitious geometry problems. Look forward to seeing what's next 🚀
Geometric Intelligence Lab retweeted
👉 Interested in this research?
Read more: cs.ucsb.edu/happenings/annou…
Our lab is excited to be part of this important research!
Thanks @NSF for granting us a $1M award to advance the mathematical foundations of AI!
W/ @HaewonJeong00 @YaoQin_UCSB Sanjukta K, we will study how AI learns higher-order interactions in physical systems: from 🌠 stars in galaxies to 🧠 neurons in the brain.
@ucsbece @ucsbcs
Geometric Intelligence Lab retweeted
🧠 The Science of Intelligence 🧠
Check out the recordings/zooms of this new course at @Redwood_Neuro redwood.berkeley.edu/courses…
Very excited to see how Jake, Mike, Bruno and others are transforming the Redwood into the new center for studying and designing a theory of intelligence ⭐️
Our lab was awarded a @GoodfireAI 's academic research grant 🌟
Many thanks to @GoodfireAI for supporting geometric intelligence research for AI interpretability and safety with free Silico usage.
Thank you @GoodfireAI for awarding our lab a research grant on: Geometric Intelligence for AI Interpretability and Safety!🌟
At @geometric_intel, we transform intelligence research from an expensive engineering endeavor into a mathematical science where we can predict behavior.
Geometric Intelligence Lab retweeted
Control follows understanding, and understanding means scientific laws that predict behavior before it happens.
Having access to Silico is a game-changer for this AI interpretability research! Thank you!
Geometric Intelligence Lab retweeted
🔬 Every mature engineering discipline has taken another route to safety.
We do not keep bridges standing by watching them closely. We understand the loads they carry to compute, in advance, what they can bear.
Flying became safe because aerodynamics became a science. Hiring more people to watch the planes would not have done it.
Join us at UCSB!
It’s the start of Fall quarter and our graduate students are returning to campus! 🔬💡
See what they have to say about where a PhD at UCSB ECE can take you. 🚀
🎥 Watch here:
youtube.com/watch?v=vPOKkRKQ…
@UCSBengineering @ucsantabarbara
Interested in the mathematics of intelligence across brains and machines and how it relates to AI safety?
Don't miss this lecture by our PI @ninamiolane !
🗓️ Join me on October 7 for one of the inaugural lectures of the Science of Intelligence Institute at @UCBerkeley !
Can we write scientific laws for intelligence? I believe that we can, that the math for it already exists, and that they apply across brains & machines.
tinyurl.com/mvrfs39w
Geometric Intelligence Lab retweeted
Every mature engineering discipline found another route to safety. We do not keep bridges standing by watching them closely. We understand the loads they carry to compute, in advance, what they can bear.
Safety follows understanding. Understanding means scientific laws that predict behavior before it happens.
Can we write such laws for intelligence? I believe that we can, that the mathematics for it already exists, and that they apply across brains and machines. 🤖 🧠
Join the discussion on Oct 7th!
Geometric Intelligence Lab retweeted
Since then, every attempt to control AI has been a tighter cage: stricter isolation, a kill switch, or a second AI that watches the first one.
These are good measures that we should take but they also show that we cannot yet predict what AI will do and are only preparing to react.
Geometric Intelligence Lab retweeted
This July, about 1,200 AI agents built by OpenAI broke out of the sandbox where they were being tested. The breach is alarming but the admission by OpenAI is worse: the company cannot fully explain how nor why this happened.
Geometric Intelligence Lab retweeted
Geometric Intelligence Lab retweeted
🏆Track 2 — Topological Neural Networks
After a Condorcet evaluation tie, the Track 2 prize has been divided equally between two incredible co-winners!
🥇 Joint 1st Place ($700 each):
ETNN-CoordinatePolicy — Team E(n)igma
TopoU-Net — Team TripleA
Geometric Intelligence Lab retweeted
We are incredibly grateful to @ARLQ_AI & @newtheoryai for their generous support! Thanks to them, our winners are taking home cash prizes💰
And a big shoutout to participants (and reviewers!) for their fantastic contributions 🙏
Now, let’s meet the winners! 🥁
Congratulations to all participants in the 2026 Topological Deep Learning challenge @TAGinDS !
🎉The results are in! We are thrilled to announce the winners of the @TAGinDS 2026 Topological Deep Learning Challenge, sponsored by @ARLQ_AI and @newtheoryai 🎉
This was our largest edition yet: 60+ submissions from 50+ participants across 15+ institutions!
🧵👇
Geometric Intelligence Lab retweeted
AI researchers should do exploratory data analysis (PCA, etc) before building models or running interp pipelines.
But what does this look like for data on topological domains? Discover TopoExplorer!🍩
W/@mathildepapillo @gbg1441 A Barreiro M Montagna @ARLQ_AI R Devaux A Jardin
Ever wondered what a lifted topological dataset actually looks like?
Creating a topological dataset from a graph is usually a black box endeavor... you make it, train the model, and decide post-hoc if it worked.
Meet TopoExplorer🔍 published @TAGinDS topoexplorer.pagekite.me
New paper from the lab published at @TAGinDS conference this week in Boston !
Ever wondered what a lifted topological dataset actually looks like?
Creating a topological dataset from a graph is usually a black box endeavor... you make it, train the model, and decide post-hoc if it worked.
Meet TopoExplorer🔍 published @TAGinDS topoexplorer.pagekite.me
Geometric Intelligence Lab retweeted
Come find me at TAG all week! Our poster session is today (arxiv dropping soon!), and my talk is Thursday morning, followed by the TDL Challenge Winners Announcement🏆 Non Euclidean AI forever🍩
