iiinova — where your digital self keeps evolving

Reposted by Mathilde Papillon

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 18/06/2026

At UCSB, Fatih is co-advised by ECE Professor @ninamiolane.bsky.social and KITP Professor Boris Shraiman. We're proud to have him in the #ECE community. Congratulations, Fatih! 👏 #AppliedMathematics #Neuroscience #NeuroAI #UCSB #ECE #SIAM

064

Reposted by Mathilde Papillon

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 18/06/2026

🎉 Congratulations to @fatihdinc.bsky.social, postdoc in UC Santa Barbara #ECE and the Kavli Institute for Theoretical Physics, on winning the Richard C. DiPrima Prize from the Society for Industrial and Applied Mathematics (SIAM). 🏆 🔗 Read the full story: lnkd.in/gd27SUAA

175

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 18/06/2026

🧠 Can geometry give us a theory of neural computation? Claire Isabel Webb and I discussed how #geometry, the hidden shapes & structure inside high-dimensional neural data, can be a powerful tool to understand how the brain computes. @longnow.org @geometric-intel.bsky.social @ucsbece.bsky.social

0196

Reposted by Mathilde Papillon

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 20/05/2026

🏥Congratulations to ECE Prof. Ramtin Pedarsani's team on receiving a UC Noyce Initiative award to develop robust vision-language models for clinical applications — part of a $3.4M UC-wide research push for computational health and cybersecurity.🤖 🔗https://tinyurl.com/mm9jb8x

275

Reposted by Mathilde Papillon

Louisa Cornelis @louisacornelis.bsky.social · 17/03/2026

🚀 Build fairer personalized ML! Our work introduces tools to evaluate trade-offs in accuracy, fairness & explanation quality. 📷Read “When ML Gets Personal” here: [arxiv.org/abs/2502.02786] @ninamiolane.bsky.social @gbg141.bsky.social

042

Reposted by Mathilde Papillon

Louisa Cornelis @louisacornelis.bsky.social · 17/03/2026

Super excited to announce that our paper, “When Machine Learning Gets Personal”, has been accepted to #ICLR2026! 🇧🇷 We propose a unified framework to reliably quantify how personalizing a model influences both prediction accuracy and explanation quality. arxiv.org/abs/2502.02786

182

Reposted by Mathilde Papillon

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 10/02/2026

🏆UCSB ranked #1 public university in the US for scientific impact, and 3rd in universities overall!🎓 Congratulations to all of our researchers who are leading the global conversation.🌐🧵 @ucsantabarbara.bsky.social @ucsbengineering.bsky.social @uofcalifornia.bsky.social

2179

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 01/12/2025

Thanks @ucsantabarbara.bsky.social for highlighting our #TIMEBestInvention of the Year award! tinyurl.com/4939bxu5 This strengthens our commitment to innovating for women's brain health with @ai-ucsb.bsky.social & @bowers-wbhi.bsky.social 🧠

1105

Reposted by Mathilde Papillon

Adele Myers @adelemyers.bsky.social · 01/12/2025

HerBrain on TIME BEST INVENTIONS OF THE YEAR! I am grateful for the opportunity to work on this project and for many interesting conversations while presenting this work. Want to learn more about how pregnancy/menstruation changes the brain? See our poster⬇️, or public talk⬇️

154

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 31/10/2025

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

1154

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 22/10/2025

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🌴

2208

Mathilde Papillon @mathildepapillon.bsky.social · 14/10/2025

We are ✨42✨ days away from the Topological Deep Learning Challenge deadline! Not sure where to start? Participating is as simple as implementing an existing graph dataset :) Win cash prizes up to 800$ USD graciously offered by #ArlequinAI or internships at UCSB and EPFL

040

Mathilde Papillon @mathildepapillon.bsky.social · 22/09/2025

🏆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!

1145

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 06/08/2025

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👇

1116

Mathilde Papillon @mathildepapillon.bsky.social · 01/08/2025

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...

15219

Mathilde Papillon @mathildepapillon.bsky.social · 15/07/2025

Hi! Who is at ICML? Feel free to reach out:) Our poster session starts tomorrow at 11am E-3101

040

Reposted by Mathilde Papillon

PLOS Biology @plosbiology.org · 11/06/2025

Can #AI become a true scientist? @ninamiolane.bsky.social explores how new technologies are reshaping scientific discovery, and why human expertise remains essential as we enter a new era of research powered by intelligent algorithms. 🧪‬ plos.io/4kZi0aB

plos.io

The fifth era of science: Artificial scientific intelligence

Can AI become a true scientist? This Perspective explores how new technologies are reshaping scientific discovery, and why human expertise remains essential as we enter a new era of research powered b...

1177

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 29/05/2025

Pregnancy &motherhood transform the brain in ways we're only beginning to understand🧠 Uncovering these changes w/ @susanacarmona.bsky.social @magdamartinezga.bsky.social @emilyjacobs.bsky.social @grotzinger.bsky.social Kaya Jordan & @cziscience.bsky.social's generous support! tinyurl.com/38jb7hm6

3298

Reposted by Mathilde Papillon

Francisco Acosta @franciscoacosta.bsky.social · 23/05/2025

We are looking for reviewers to serve on the Program Committee of the Symmetry and Geometry in Neural Representations (NeurReps) workshop at NeurIPS 2025! If you are interested in participating, please fill out this form: forms.gle/wgUXHT7Mq71n... @neurreps.bsky.social

0208

Mathilde Papillon @mathildepapillon.bsky.social · 19/05/2025

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/

1229

Mathilde Papillon @mathildepapillon.bsky.social · 13/05/2025

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🍩

074

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 05/03/2025

How can neural nets extract *interpretable* features from data—& uncover new science? 👉 Discover our mathematical framework tackling this question w/ identifiability theory, compressed sensing, interpretability & geometry!🌐 By @david-klindt.bsky.social @rpatrik96.bsky.social C. O'Neill H Maurer

0198

Reposted by Mathilde Papillon

David Klindt @david-klindt.bsky.social · 04/03/2025

🔵 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

arxiv.org

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...

1267

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 03/03/2025

How does AI memorize information? How does ChatGPT remember your name? How do RNNs keep track of simple numbers? Our new paper led by Bariscan Kurtkaya & Fatih Dinc explores the geometry of short-term memory in neural networks—revealing limits in how information is stored!🧵 arxiv.org/abs/2502.17433

1148

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 25/02/2025

🤖 New Talk: Geometric Intelligence in Minds & Machines 🧠 Available on Youtube: www.youtube.com/watch?v=1RtH... @louisacornelis.bsky.social & I opened the 2025 @neurreps.bsky.social Global Speaker Series ! Thanks @mathildepapillon.bsky.social Chase VDG @btolooshams.bsky.social for hosting!

youtube.com

Episode #7 | Nina Miolane & Louisa Cornelis

YouTube video by NeurReps

1125

Reposted by Mathilde Papillon

Louisa Cornelis @louisacornelis.bsky.social · 22/02/2025

Thanks for hosting this Mathilde!

1115

Mathilde Papillon @mathildepapillon.bsky.social · 21/02/2025

Thank you to everyone who showed up in person and online! Congrats to @ninamiolane.bsky.social and @louisacornelis.bsky.social for some stellar talks🤩

183

Reposted by Mathilde Papillon

Bahareh Tolooshams @btolooshams.bsky.social · 19/02/2025

Join us remotely or in person to hear from @ninamiolane.bsky.social and @louisacornelis.bsky.social on Geometric Intelligence in Minds and Mahcines. Thanks, @mathildepapillon.bsky.social, for hosting!

043

Reposted by Mathilde Papillon

Olga Zaghen @olgatticus.bsky.social · 19/02/2025

Variational Flow Matching goes Riemannian! 🔮 In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results. Dream team: Floor, Alison & Erik (their @ below) 💥 📜 arxiv.org/abs/2502.12981 🧵1/5

13512

Mathilde Papillon @mathildepapillon.bsky.social · 19/02/2025

I am excited to host the next edition of the NeurReps Global Seminar Series, from @neurreps.bsky.social! @ninamiolane.bsky.social and @louisacornelis.bsky.social will be speaking on 🧠Geometric Intelligence in Minds and Machines🤖 📅Friday, Feb 21st, 11am PST Join us at UCSB (Elings,1605) or on Zoom!

0238

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 12/02/2025

Incredibly grateful to @cziscience.bsky.social for this second award supporting our work in AI for women’s brain health @bowers-wbhi.bsky.social !🌟 The WBHI advances healthcare for all by developing inclusive AI on multi-modal biomedical datasets that include phenotypes relevant to women's health.

0197

Reposted by Mathilde Papillon

Geometric Intelligence Lab @geometric-intel.bsky.social · 06/02/2025

Your phone’s facial recognition, the internet, and futuristic LEDs - what do they all have in common? Light! Santa Barbara folks📢: Please join us Tuesday Feb. 18th at 6pm, at Brass Bear Brewing in downtown SB for Roark Chao's talk on using metasurfaces to control light⚡️🔦

031

Reposted by Mathilde Papillon

Javier E. Fernandez @javif86.bsky.social · 06/02/2025

Enjoying and learning a lot from this piece! I don’t know if the best reading choice for a week of holiday 🤣🤯 but 100% recommended if you are like me still getting your head around TDL/GDL. @mathildepapillon.bsky.social and co-authors 🙌👏 arxiv.org/pdf/2407.09468

0124

Reposted by Mathilde Papillon

Graph Signal Processing Workshop 2025 @gsp-workshop.bsky.social · 26/01/2025

We’re absolutely thrilled to have an exciting lineup of speakers this year covering a wide range of topics, including @pseudomanifold.topology.rocks @dom-beaini.bsky.social @mathildepapillon.bsky.social Dhananjay Bhaskar, Naoki Saito!

0133

Mathilde Papillon @mathildepapillon.bsky.social · 08/01/2025

Math friends! I am at JMM in Seattle all week, feel free to reach out🍩 To learn more about Topological Deep Learning, join me in two talks! - room 607 at 9:30am today in the Special Session on Topological Machine Learning in - or room 613 tomorrow at 3:30pm

0114

Reposted by Mathilde Papillon

Geometric Intelligence Lab @geometric-intel.bsky.social · 07/01/2025

What a start to 2025!🎉 Our lab is honored to receive $1M from @cziscience.bsky.social @chanzuckerberg.bsky.social to study how motherhood shapes the brain, focusing on maternal mental health. @ninamiolane.bsky.social @susanacarmona.bsky.social @emilyjacobs.bsky.social @magdamartinezga.bsky.social

1188

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 07/01/2025

Happy New Year🎉 Thrilled to start 2025 with $1M from @cziscience.bsky.social @chanzuckerberg.bsky.social to study the maternal brain using AI! Grateful for the chance to advance science for mothers worldwide 🧠 @emilyjacobs.bsky.social @susanacarmona.bsky.social @magdamartinezga.bsky.social

Picture credits: Susana Carmona's Book Cover. Neuromaternal.

34012

Reposted by Mathilde Papillon

Sharvaree Vadgama @sharvaree.bsky.social · 12/12/2024

Loving bsky community. Since I joined, I got to meet a lot of new people especially women in ML/AI! It's really heart warming to see that there are so many incredible women doing really cool work especially on the days when you face the challenges of working in severely skewed gender ratio groups.

1191

Reposted by Mathilde Papillon

christian-shewmake.bsky.social @christian-shewmake.bsky.social · 09/12/2024

Excited to talk with the community about what we've been working on! Co-founding @newtheory.ai with @colin-r-odonnell.bsky.social to build new foundational architectures for intelligence. Come join us at NeurIPS in Vancouver this week for our soft-launch event 🎊🥂 partiful.com/e/rgVdt2XkzZ...

partiful.com

RSVP to New Theory Soft Launch! | Partiful

Spun out of Berkeley/Redwood Center, New Theory is building new foundational models rooted in Geometric Deep Learning that break the scaling laws of transformer-based architectures, paving the way for...

1207

Mathilde Papillon @mathildepapillon.bsky.social · 09/12/2024

Thank you CohereForAI @cohere.com for having me! Always so fulfilling to witness the growing excitement around geometry/topology/algebra in machine learning🤩 For anyone who is interested and missed our convo last Thursday, check out the recording here! www.youtube.com/watch?v=g3fe...

youtube.com

Mathilde Papillon - Beyond Euclid: An Illustrated Guide to Modern Machine Learning...

YouTube video by Cohere

0114

Reposted by Mathilde Papillon

Nina Miolane @ninamiolane.bsky.social · 02/12/2024

Hi Bluesky! I’m an Assist Prof at UCSB’s Geometric Intelligence Lab @geometric-intel.bsky.social, decoding the geometric signatures of intelligence 🧠✨ We bridge physics, neuro, math & AI to uncover how intelligence emerges + build intelligent models to advance the brain sciences! gi.ece.ucsb.edu

gi.ece.ucsb.edu

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.

14711

Mathilde Papillon @mathildepapillon.bsky.social · 02/12/2024

This should be fun! I'll be sharing our recent literature review on all things geometric/topological/algebraic ML✨🍩 With @naturecomputes.bsky.social Johan Mathe, D. Buracas, H. Lillemark, C. Shewmake, @abbybertics.bsky.social , X. Pennec, and @ninamiolane.bsky.social

0106