@ai-ucsb.bsky.social
📤 24
📥 11
📝 6
reposted by
Nina Miolane
6 days ago
Congrats to Sarah Kushner Luís F. Pereira
@adelemyers.bsky.social
@louisacornelis.bsky.social
Laura Pritschet Sheila S. Daniel Martin de Blas Hannah Grotzinger Ina Stelzer Liz Chrastil Kaitlin Casaletto Kaya Jordan
@susanacarmona.bsky.social
@magdamartinezga.bsky.social
@emilyjacobs.bsky.social
🧠
0
6
3
reposted by
Nina Miolane
6 days ago
Thrilled to see HerBrain on
#TIME
Best Inventions of 2025! It shows how the anatomy of the brain changes week-by-week through pregnancy and postpartum 🧠
@geometric-intel.bsky.social
@ai-ucsb.bsky.social
@bowers-wbhi.bsky.social
@neuromaternal.bsky.social
!
1
11
5
reposted by
Geometric Intelligence Lab
23 days ago
Rumor has it Mother Nature might be the best AI engineer🌱💡 Come see why at Brass Bear Brewing, Nov 13 @ 6pm. With Dr. Fatih Dinc, we’ll dive into how brains, bots, and biology compute with intelligence
0
8
3
reposted by
Nina Miolane
about 1 month ago
The second paper called "On the Approximation of the Riemannian Barycenter" uses the bounds from the above article to compute approximations of the Riemannian barycenter at very low computational cost!
link.springer.com/chapter/10.1...
0
7
2
reposted by
Nina Miolane
about 1 month ago
The first paper called "Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics" studies the geometry of the Stiefel manifold to derive simple and insightful bounds on the computationally untractable geodesic distance.
sciencedirect.com/science/arti...
1
4
2
reposted by
Nina Miolane
about 1 month ago
Thrilled to see these two papers by Simon Mataigne, co-authored with P.-A. Absil published this month 🤩 They connect deep mathematical theory to practical algorithms on the Stiefel manifold and the approximation of the Riemannian barycenter 🌐 Details & papers👇
@geometric-intel.bsky.social
1
15
5
reposted by
Nina Miolane
about 1 month ago
We are physicists, neuroscientists, mathematicians and computer scientists who study intelligence in biological and artificial neural networks and use our findings to build better AI models. 👉 You can join us via UCSB ECE, CS, Math or DYNS PhD programs!
1
6
3
reposted by
Nina Miolane
about 1 month ago
You are specifically interested in AI? 👉 Look at the AI Curriculum from the UCSB Real AI Initiative offered within the CS and the ECE departments.
ai.ece.ucsb.edu/ai-ucsb
@ai-ucsb.bsky.social
@ucsbece.bsky.social
@ucsb-cs.bsky.social
@ucsbengineering.bsky.social
loading . . .
AI Curriculum — REAL AI
https://ai.ece.ucsb.edu/ai-ucsb
1
4
3
reposted by
Nina Miolane
about 1 month ago
From your desk you'll see dolphins, beach volleyball courts, surf spots & more importantly: your colleagues!
@adelemyers.bsky.social
@mathildepapillon.bsky.social
@franciscoacosta.bsky.social
@louisacornelis.bsky.social
@abbybertics.bsky.social
@bariskurtkaya.bsky.social
and
gi.ece.ucsb.edu/people
1
6
3
reposted by
Nina Miolane
about 1 month ago
Details on our research and how to apply to our lab are on our website:
gi.ece.ucsb.edu
. We hope to hear from you! 👋
@uofcalifornia.bsky.social
@ucsantabarbara.bsky.social
@ucsbece.bsky.social
@ucsb-cs.bsky.social
@geometric-intel.bsky.social
loading . . .
The Geometric Intelligence Lab @ UC Santa Barbara
The mission of the Geometric Intelligence Lab is to reveal the geometric signatures of natural and artificial intelligence.
https://gi.ece.ucsb.edu
0
5
3
reposted by
Nina Miolane
about 1 month ago
I am recruiting PhD students for 2026!😃 You want to reveal the geometric signatures of natural and artificial intelligence, and understand computations in brains and AI? 🌐🧠🤖 Apply to the UCSB Geometric Intelligence Lab ✨ This is the view you'd have from... your desk🌴
2
20
9
reposted by
The Robert Mehrabian College of Engineering
about 2 months ago
UCSB physics professors John Martinis and Michel Devoret have been awarded the 2025 Nobel Prize in Physics. They were lauded for work that, according to the Royal Swedish Academy of Sciences, "revealed quantum physics in action," affirming UCSB as the epicenter of quantum research.
1
4
3
reposted by
Nina Miolane
about 2 months ago
Two more Nobel Prizes at
@ucsantabarbara.bsky.social
, congratulations !!
add a skeleton here at some point
0
4
3
reposted by
Nina Miolane
about 2 months ago
The UC sets a new world record with 5 Nobel Prizes this year!
0
5
3
reposted by
Mathilde Papillon
2 months ago
A huge thank you to our partners! 🤝 💰 Cash prizes are sponsored by the brilliant team at Arlequin AI. 🏛️ Internships are hosted by the world-class UC Santa Barbara
@geometric-intel.bsky.social
and EPFL IMOS labs.
1
5
3
reposted by
Mathilde Papillon
2 months ago
We can't wait to see your innovative solutions! Full details on the tasks and data are on our site: 🔗
geometric-intelligence.github.io/topobench/td...
#TDLChallenge
#AI
#ML
#TAGinDS
0
7
3
reposted by
Mathilde Papillon
2 months ago
🏆The 2025 Topological Deep Learning Challenge is officially live!🏆 Hosted by the TAGinDS Conference 2025 🚀 This year, push the boundaries of topological ML by “Expanding the Data Landscape” 💰 Win incredible prizes, including research internships at UCSB and EPFL, as well as up to $800 US in cash!
1
14
9
reposted by
Lev Telyatnikov
3 months ago
We can’t wait to see what the community builds with TopoBench! Star our repo, read the paper, and bring reproducibility to your TDL research. Contributions and feedback are welcome!
#OpenSource
#Python
#AcademicTwitter
0
6
4
reposted by
Lev Telyatnikov
3 months ago
This was a massive team effort! Developed & led by
@levtelyatnikov.bsky.social
,
@gbg141.bsky.social
, Theodore Papamarkou. With major contributions from @Marco Montagna, Mustafa Hajij, Ghada Zamzmi, Michael T. Schaub,
@ninamiolane.bsky.social
, &
@sscardapane.bsky.social
, and many others!
1
6
4
reposted by
Lev Telyatnikov
3 months ago
For a deep dive into our framework for reproducible benchmarking, our methodology, and key findings, check out the full paper. Paper:
arxiv.org/abs/246.06642
#MachineLearning
#GNN
#DataScience
loading . . .
http://arxiv.org/abs/246.06642
1
5
3
reposted by
Lev Telyatnikov
3 months ago
At its core, TopoBench is a framework for robust and fair evaluation in TDL. We’re empowering researchers and practitioners to compare models with confidence and push the field forward, together.
1
4
2
reposted by
Lev Telyatnikov
3 months ago
Curious about topological liftings? TopoBench lets you experiment with them on your own data! We’ve included 20+ liftings from last year’s TDL Challenge @TAGinDS, @PyT_Team_. Explore them all in our Wiki:
github.com/geometric-in...
#TDA
loading . . .
Structural Liftings
TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning - geometric-intelligence/TopoBench
https://github.com/geometric-intelligence/TopoBench/wiki/Structural-Liftings
1
4
3
reposted by
Lev Telyatnikov
3 months ago
Struggling with reproducible benchmarks in TDL? We’ve got you covered. 12+ models tested on 22+ diverse, cross-domain datasets. Tutorials to get you started with topology & higher-order homophily Webpage/Docs:
geometric-intelligence.github.io/TopoBench/
loading . . .
TopoBench
TopoBench: A comprehensive benchmarking framework for Topological Deep Learning models and datasets.
https://geometric-intelligence.github.io/TopoBench/
1
3
3
reposted by
Lev Telyatnikov
3 months ago
Delighted to announce TopoBench has been accepted to DMLR! It’s a modular library for Topological Deep Learning, built to provide reproducible, cross-domain benchmarks and accelerate research. GitHub:
github.com/geometric-in...
#AI
#DeepLearning
loading . . .
GitHub - geometric-intelligence/TopoBench: TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning
TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning - geometric-intelligence/TopoBench
https://github.com/geometric-intelligence/TopoBench
1
13
6
reposted by
Nina Miolane
3 months ago
We are recruiting postdocs
@ai-ucsb.bsky.social
! With
@haewonjeong.bsky.social
Yao Qin You want to lead the future of AI4Science? Apply to UCSB Real AI For Science Initiative 🌟 Deadline: Sept 15, 2025. This is the view you'll have from... your desk! By
@adelemyers.bsky.social
1
7
6
Collaboration is what makes UCSB so special✨. Can’t wait to welcome new postdocs to the AI4Science community!
add a skeleton here at some point
3 months ago
0
1
1
reposted by
Nina Miolane
3 months ago
Our research is collaborative at heart: We work with neuroscientists, physicists, and healthcare professionals to design principled AI that is tailored to data-scarce scientific fields. You’ll join a vibrant AI community on the golden Californian coast
@uofcalifornia.bsky.social
🌴
1
3
3
reposted by
Nina Miolane
3 months ago
Discover our research:
ai.ece.ucsb.edu/publications
Apply: Send CV + coverletter 📩 to
[email protected]
🕐 by Sept 15, 2025 to receive full consideration. We hope to hear from you!
@ucsantabarbara.bsky.social
@ucsb-cs.bsky.social
@ucsbece.bsky.social
@ucsbengineering.bsky.social
0
5
3
reposted by
Geometric Intelligence Lab
4 months ago
From the lab to the airwaves 🎙️: Our PI
@ninamiolane.bsky.social
joined Anita Okorie on Mind Over Matter for a fascinating conversation on geometric AI, brain complexity, and how neuroimaging is helping to understand neurodegenerative disease. 🎧 Listen here:
tinyurl.com/mryct7h9
add a skeleton here at some point
0
4
2
reposted by
Nina Miolane
4 months ago
Interested in how geometric intelligence emerges in brains and machines? 🧠➗🤖 I joined Anita Okorie on Mind Over Matter to discuss geometric AI, brain complexity, and how neuroimaging can advance our understanding of neurodegenerative diseases. 🎧 Episode
tinyurl.com/mryct7h9
0
12
5
reposted by
Geometric Intelligence Lab
4 months ago
Been waiting for this one😼! A beautiful, digestible guide to non-Euclidean ML — gorgeous visuals, clean tables, and clear explanations of topology, algebra, and geometry. Dive in 👇
add a skeleton here at some point
0
1
1
reposted by
Mathilde Papillon
4 months ago
The updated version is also available on arxiv at
arxiv.org/pdf/2407.09468
loading . . .
https://arxiv.org/pdf/2407.09468
1
9
3
reposted by
Mathilde Papillon
4 months ago
Thank you to the excellent team of editors
@iopp-mlresearch.bsky.social
and our referees for a truly productive peer review process. Highly recommend this up and coming journal for any unsubmitted topical reviews out there!
1
6
3
reposted by
Mathilde Papillon
4 months ago
Made possible with the (equal) dedication of
@naturecomputes.bsky.social
Johan Mathe
@louisacornelis.bsky.social
and the contributions of
@abbybertics.bsky.social
, Domas Buracas, Hansen Lillemark,
@christian-shewmake.bsky.social
,
@fatihdinc.bsky.social
Xavier Pennec and
@ninamiolane.bsky.social
1
7
2
reposted by
Mathilde Papillon
4 months ago
Our illustrated guide to non-Euclidian ML is finally published! Check it out for ⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field ⭐️ broken down tables for easy reading ⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
1
52
24
reposted by
Nina Miolane
5 months ago
Congratulations! Looking forward to seeing the research that will come out of your lab 🤩
add a skeleton here at some point
0
2
1
reposted by
Nina Miolane
4 months ago
Many thanks to
@mathildepapillon.bsky.social
@naturecomputes.bsky.social
J. Mathe
@louisacornell.bsky.social
@abbybertics.bsky.social
D. Buracas H. Lillemark
@christian-shewmake.bsky.social
@fatihdinc.bsky.social
X. Pennec for this collaboration !
0
5
2
reposted by
Nina Miolane
4 months ago
In the 20th century, non-Euclidean geometry transformed how we model the world with pen and paper. Now, it is disrupting how we model the world with machines. Learn more in our illustrated guide to non-Euclidean ML and AI👇
add a skeleton here at some point
1
11
6
reposted by
Nina Miolane
6 months ago
The era of artificial scientific intelligence is here. As algorithms generate discoveries at scale, what role remains for human scientists? 🤔 Thanks
@plosbiology.org
for publishing my perspective
@ucsantabarbara.bsky.social
@ai-ucsb.bsky.social
@ucsbece.bsky.social
@ucsb-cs.bsky.social
🌟
add a skeleton here at some point
1
14
9
reposted by
Nina Miolane
6 months ago
Watch the 2025 winners explain their solution predicting ADHD across sexes🧠: 📺
youtu.be/i6XdxAa9Bak
Thanks to Valerie Elliott Arianna Zuanazzi
@amykooz.bsky.social
Maggie Demkin
@bowers-wbhi.bsky.social
@kaggle.com
@childmindinstitute.bsky.social
for organizing! Congrats to all the participants!
loading . . .
WiDS Datathon 2025 Winners Panel Discussion
YouTube video by WiDS Worldwide
https://youtu.be/i6XdxAa9Bak
0
6
5
reposted by
Nina Miolane
6 months ago
Congrats to the winners of the 2025 Global Datathon on Women's Brain Health: 🥇 Manh Nguyen, Thu Nguyen -FPT University 🥈 Baixue Yao, Xiaoyue Zhang -Flagship Labs 84 🥉 Wei Lyu, Zhida Wang
@ucsantabarbara.bsky.social
(!) selected from 1000+ participants around the globe! 🌐
@bowers-wbhi.bsky.social
1
6
5
reposted by
Nina Miolane
6 months ago
At last Topological Neural Networks are fast🚀 HOPSE builds an encoder for combinatorial complexes, enabling topological deep learning (TDL) w/o the usual computational cost. A major step forward for TDL!
@martinca.bsky.social
@gbg141.bsky.social
@marcomonga.bsky.social
@levtelyatnikov.bsky.social
add a skeleton here at some point
0
7
5
reposted by
Martin Carrasco
6 months ago
Empirically we find that 𝐇𝐎𝐏𝐒𝐄 👀: ⚡Outperforms (speed and performance) GNNs in larger datasets (MANTRA) 🥇Achieves SOTA on Topological Tasks -- predicting Betti numbers 1 & 2 on MANTRA 📈 Is: faster, more accurate, scalable (5/6)
1
5
5
reposted by
Martin Carrasco
6 months ago
TDL actually works at scale! And we believe 𝐇𝐎𝐏𝐒𝐄 lays the foundation for broad applications of TDL ✨ 📭 Reach out for collaborations Special thanks to
@levtelyatnikov.bsky.social
and @gbg1441 and the team
@ninamiolane.bsky.social
and @Coerulatus :) (6/6)
0
7
5
reposted by
Lev Telyatnikov
6 months ago
Absolutely proud of this work! Huge thanks to
@gbg141.bsky.social
@ninamiolane.bsky.social
@marcomonga.bsky.social
— and of course
@martinca.bsky.social
, who drove the project, learned on the fly, and kept the enthusiasm high at every turn!
add a skeleton here at some point
1
8
5
reposted by
David Klindt
9 months ago
🔵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability. If you’re curious about lifting neural reps out of superposition, this might interest you! 🤓
arxiv.org/abs/2503.01824
loading . . .
From superposition to sparse codes: interpretable representations in neural networks
Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence sugg...
https://arxiv.org/abs/2503.01824
1
24
10
reposted by
Mathilde Papillon
7 months ago
Come find me
@gsp-workshop.bsky.social
at MILA all week! Can’t wait to be back in Montreal connecting with the community🕸️ I’ll be speaking on purely graph-based (!) Topological Deep Learning first thing tomorrow at 9am. Let’s kick off this workshop in style🍩
add a skeleton here at some point
0
7
4
reposted by
Mathilde Papillon
7 months ago
Thank you Guillermo Bernárdez,
@clabat9.bsky.social
@ninamiolane.bsky.social
for making this work possible! 🏠
@geometric-intel.bsky.social
@ucsb.bsky.social
0
7
5
reposted by
Mathilde Papillon
7 months ago
🍩TopoTune takes any neural network as input and builds the most general TDL model to date, complete with permutation equivariance and unparalleled expressivity. ⚙️ Thanks to its implementation in TopoBench, defining and training these models only requires a few lines of code.
1
7
5
reposted by
Mathilde Papillon
7 months ago
TopoTune is going to ICML 2025!🎉🇨🇦 Curious to try topological deep learning with your custom GNN or your specific dataset? We built this for you! Find out how to get started at
geometric-intelligence.github.io/topotune/
1
22
10
Load more
feeds!
log in