Geometric Intelligence Lab
Research lab at UCSB Engineering revealing the geometric signatures of nature and artificial intelligence | PI: @ninamiolane.bsky.social
- Love to see it from @fatihdinc.bsky.social 😼🐼 Looking forward to seeing future talks from @ai-ucsb.bsky.social @ucsbece.bsky.social
- We’re excited to kick off this year’s REAL AI Seminar Series! 🤖✨ Thrilled to start with @fatihdinc.bsky.social , thanks for joining us to launch the series. Dr. Fatih Dinc gave a wonderful talk on biological versus artificial neural networks 🤯 @ucsbece.bsky.social @geometric-intel.bsky.social
- Reposted by Geometric Intelligence LabWe’re excited to kick off this year’s REAL AI Seminar Series! 🤖✨ Thrilled to start with @fatihdinc.bsky.social , thanks for joining us to launch the series. Dr. Fatih Dinc gave a wonderful talk on biological versus artificial neural networks 🤯 @ucsbece.bsky.social @geometric-intel.bsky.social
- Reposted by Geometric Intelligence LabIf you are passionate about shaping the next generation of global tech leaders and want to run a program at the intersection of world-class research and professional excellence, we want to hear from you!
- Reposted by Geometric Intelligence LabWe are looking for a visionary leader to serve as the inaugural Executive Director for this first-of-its-kind program @ucsbengineering.bsky.social @ucsantabarbara.bsky.social. lnkd.in/gbe5fhHU
- Reposted by Geometric Intelligence LabDesigned for early/mid career tech professionals, METL bridges the gap btw deep technical expertise & strategic business leadership. Fall 2026: Specialized tracks in Semiconductor Technology & Technology Management. Fall 2027: Quantum Information & AI for Science and Technology.
- Reposted by Geometric Intelligence LabExciting News! 🎓✨ Our new online professional master’s program—the Master of Engineering and Technology Leadership (METL)—is launching in Fall 2026: We Are Hiring its Executive Director! Join us in building the future of engineering @ucsantabarbara.bsky.social: lnkd.in/gbe5fhHU
- Winter Quarter is here @ucsantabarbara.bsky.social but the classroom has changed. How do we teach and learn when AI tools think & write faster? GI Lab's PhD @abbybertics.bsky.social explores innovation vs academic integrity in a podcast #TheEconomist also featuring PI @ninamiolane.bsky.social 🎙️👇
- @abbybertics.bsky.social s reports from campus about an education system in crisis, and asks what the future might look like as students begin to tap into a tool that can think quicker, write faster and teach better than many of their instructors. 🎙️Listen here: www.economist.com/podcasts/202... !
- [This post could not be retrieved]
- @abbybertics.bsky.social s reports from campus about an education system in crisis, and asks what the future might look like as students begin to tap into a tool that can think quicker, write faster and teach better than many of their instructors. 🎙️Listen here: www.economist.com/podcasts/202... !
- Thrilled to share @ninamiolane.bsky.social 's OpEd in @insidehighered.com with Annie K. Lamar! Open-source software and scientific infrastructure fuel discovery by removing barriers – not creating them. Time to start treating open science as the public good it is🔬💡
- Thanks @insidehighered.com for publishing our OpEd w Annie K. Lamar #publicvoices of The Oped Project @ucsantabarbara.bsky.social ! 🤖Open source software & infra accelerates scientific discoveries by removing financial & technical barriers. It's about time we start treating it as a public good👇
- Reposted by Geometric Intelligence LabThe way forward is to invest in true open-source software and infrastructure. Read our full oped w/ Annie K. Lamar @ucsantabarbara.bsky.social #publicvoices of TheOpEdProject: insidehighered.com/opinion/view... @geometric-intel.bsky.social @ai-ucsb.bsky.social @ucsbengineering.bsky.social
- Reposted by Geometric Intelligence Lab🙌 To be sure, *some* companies are truly dedicated to open-source. By generously sharing their resources, they have dramatically advanced science. It's time universities do the same.
- Reposted by Geometric Intelligence Lab👩🔬 Science advances slowly, across decades. Commercial tools, by contrast, advance quickly through mergers, pivots and quarterly earnings reports. Tethering our infrastructure to private companies is like writing knowledge in disappearing ink.
- Reposted by Geometric Intelligence Lab🦾 If we continue to rent the foundations of our knowledge from private companies, we should not be surprised when the floor gives way beneath us.
- Reposted by Geometric Intelligence Lab💵 Without proper funding structures, essential research tools remain fragile, often maintained by overworked volunteers. Universities must begin funding engineers at competitive salaries and recognizing software development as a legitimate form of scholarship.
- Reposted by Geometric Intelligence Lab👩💻 Universities are reluctant to fund software engineers at competitive salaries. A skilled engineer can earn 5x more in industry than in academia, yet most grants deprioritize dedicated engineering roles.
- Reposted by Geometric Intelligence Lab🤔 Much of modern research rests on tools and platforms maintained not by universities or public institutions, but by corporations whose priorities can shift overnight. Knowledge itself is being built on the shifting sand of corporate discretion.
- Reposted by Geometric Intelligence LabWe present graph-based neural surrogates that enable fast and uncertainty-aware emulation of global hybrid-Vlasov simulations via a probabilistic latent-variable model. Data + code are openly available, and compatible with advances happening in data-driven weather prediction!
- Reposted by Geometric Intelligence LabAre you interested in ML for space/plasma physics? I'll be presenting “Graph-based Neural Space Weather Forecasting” this Saturday at the ML for physics workshop in San Diego @neuripsconf.bsky.social 🚀 📄 Paper: arxiv.org/abs/2509.19605 💻 Code: github.com/fmihpc/space... #AI4Science #ML4PS
- A special thank you to @ucsantabarbara.bsky.social for the thoughtful article on HerBrain – capturing our mission and the importance of understanding how pregnancy shapes the brain 🧠 tinyurl.com/4939bxu5 #TIMEBestInventions #WomensBrainHealth @ai-ucsb.bsky.social @bowers-wbhi.bsky.social
- 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 🧠
- Reposted by Geometric Intelligence LabHuge thanks to S. Kushner L. Pereira @adelemyers.bsky.social @louisacornelis.bsky.social L. Pritschet Sheila S. D. Martin de Blas H. Grotzinger I. Stelzer L. Chrastil K. Casaletto K. Jordan @susanacarmona.bsky.social @magdamartinezga.bsky.social @emilyjacobs.bsky.social 🧠
- Reposted by Geometric Intelligence LabReally enjoyed this recent interview on my work with the Dodgers and how the @geometric-intel.bsky.social lab prepared me for it! Thank you for having me UCSB⚾️ Check it out here science.ucsb.edu/news/geometr...
- Reposted by Geometric Intelligence LabCongrats 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 🧠
- Reposted by Geometric Intelligence LabThrilled 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 !
- 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
- Huge congrats to Simon Mataigne and P.-A. Absil on two new papers out this month! 🎉 Bringing elegant math to life through algorithms on the Stiefel manifold and Riemannian barycenters🌐
- 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
- Reposted by Geometric Intelligence LabThe 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...
- Reposted by Geometric Intelligence LabThe 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...
- 🚀We’re recruiting PhD students for 2026! If you’re passionate about uncovering the geometric signatures of intelligence in brains🧠 and AI🤖, we’d love to hear from you! Join us in exploring the computations that power natural and artificial minds. 🌐✨
- And yes, we do play volleyball on the beach nearby🏐🌴
- Details on our research and how to apply to our lab are on our website: gi.ece.ucsb.xn--edu-v113b @uofcalifornia.bsky.social @ucsantabarbara.bsky.social @ucsbece.bsky.social @ucsb-cs.bsky.social
- Reposted by Geometric Intelligence LabDetails 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
- Reposted by Geometric Intelligence LabFrom 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
- Reposted by Geometric Intelligence LabYou 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
- Reposted by Geometric Intelligence LabWe 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!
- Reposted by Geometric Intelligence LabTwo more Nobel Prizes at @ucsantabarbara.bsky.social , congratulations !!
- Reposted by Geometric Intelligence LabThe UC sets a new world record with 5 Nobel Prizes this year!
- Reposted by Geometric Intelligence LabWe 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
- Reposted by Geometric Intelligence LabA 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.
- Prizes, research gigs, and a chance to twist data into new shapes with topology + ML? 👾 Count me in for the Topological Deep Learning Challenge 2025! 🌀 Who else is ready to expand the data universe?
- Diving into topological deep learning🌀? Check out TopoBench — a unified framework for rigorous benchmarking of TDL models. Pleased to share it has been accepted to DMLR! Code & paper: geometric-intelligence.github.io/TopoBench/
- 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
- Reposted by Geometric Intelligence LabStruggling 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/
- Reposted by Geometric Intelligence LabCurious 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
- Reposted by Geometric Intelligence LabAt 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.
- Reposted by Geometric Intelligence LabFor 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
- Reposted by Geometric Intelligence LabThis 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!
- Reposted by Geometric Intelligence LabWe 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
- Cutting-edge AI4Science research with the ocean at your doorstep? I'm interested👓🥼 At UCSB, we build AI methods that accelerate discovery – from neuroscience to physics to healthcare. Join @ai-ucsb.bsky.social and help shape the future of AI4Science!
- 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
- Reposted by Geometric Intelligence LabOur 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 🌴
- Reposted by Geometric Intelligence LabDiscover our research: ai.ece.ucsb.edu/publications Apply: Send CV + coverletter 📩 to ai@ece.ucsb.edu 🕐 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
- 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
- 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
- Reposted by Geometric Intelligence LabIn 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👇
- 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...
- Reposted by Geometric Intelligence LabThe updated version is also available on arxiv at arxiv.org/pdf/2407.09468
- Reposted by Geometric Intelligence LabThank 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!
- Reposted by Geometric Intelligence LabMade 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
- 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 👇
- 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...
- 🚨One of the coolest workshops in AI is back! NeurReps 2025 is calling for papers on symmetry, geometry & topology in neural networks 🧠📐 If your work bridges theory & structure — don’t miss this. 📅 Deadline: Aug 22
- 📢 Call for Papers: NeurReps 2025 ‼️‼️‼️ 🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks. Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages). Deadline: Aug 22, 2025. www.neurreps.org/call-for-pap...
- Reposted by Geometric Intelligence LabFeaturing @haewonjeong.bsky.social and Yao Qin from @ai-ucsb.bsky.social !
- Check out a new perspective from @ninamiolane.bsky.social on the role of human scientists in an era where discoveries by artificial intelligence are increasing 🧠👽
- 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 🌟
- Reposted by Geometric Intelligence LabThe 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 🌟
- 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
- Watch the winning team's approach to predicting ADHD across sexes🧠👏Incredible work from this year’s champions!
- 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!
- Incredible work from 1000s of minds across continents advancing women's brain health. Big congrats to these standout teams! 🧠🌍
- 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
- Discover our lab's research with the @bowers-wbhi.bsky.social on building AI models of the maternal brain @neuromaternal.bsky.social !🤰🧠 Thanks, @ucsbengineering.bsky.social , for the feature! Read more:👇
- 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
- 🚨 New preprint from the lab! Discover fast topological neural networks, that leverage higher order structures without the usual computational burden! By @martinca.bsky.social @gbg141.bsky.social @marcomonga.bsky.social @levtelyatnikov.bsky.social @ninamiolane.bsky.social
- 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
- Reposted by Geometric Intelligence LabEmpirically 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)
- Reposted by Geometric Intelligence LabThe model relies on positional and structural encodings (PSE) of the combinatorial domain. By decomposing a combinatorial representation into neighborhoods which take the form of a Hasse graph, the PSE of each can be used to discard the topology and learn from the PSE! (4/6)
- Reposted by Geometric Intelligence LabHowever, with 𝐇𝐎𝐏𝐒𝐄 ✅ Higher-order expressivity (> CCWL) 😱 ✅ Linear scaling wrt dataset size 🔥 ✅ No message passing 💡 ✅ Higher-order Positional and Structural encodings (PSEs) for ANY combinatorial representation (3/6)
- Reposted by Geometric Intelligence LabHOMP (higher-order message passing) networks are more expressive than traditional message passing GNNs but significantly more costly 💣💥! (2/6)
- Reposted by Geometric Intelligence Lab🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better? Introducing: 🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀 📝 arXiv: arxiv.org/abs/2505.15405 🧵 (1/6)
-
View full threadReposted by Geometric Intelligence LabTDL 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)
- Reposted by Geometric Intelligence LabAbsolutely 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!
- 🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better? Introducing: 🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀 📝 arXiv: arxiv.org/abs/2505.15405 🧵 (1/6)
- Reposted by Geometric Intelligence Lab🍩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.
