🏆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!

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

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

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 🌴

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

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

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...

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 !

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👇

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 🌟

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!

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

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)

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

🚨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)

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!

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🍩

Thank you Guillermo Bernárdez, @clabat9.bsky.social @ninamiolane.bsky.social for making this work possible! 🏠 @geometric-intel.bsky.social @ucsb.bsky.social

🍩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.

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/

#UCSB researchers have unveiled advancements in 3D semiconductor technology. “This breakthrough represents a major step toward the next generation of transistor technologies that can sustain the rapid progress of computing and artificial intelligence applications." news.ucsb.edu/2025/021805/...

A team of researchers, including UCSB chemical engineering professor Phillip Christopher and PhD student, Anika Jalil, have discovered a way to potentially reduce CO2 emissions and decrease the need for chlorine to produce this ubiquitous chemical, by adding nickel atoms to the silver catalyst.

Congratulations to Umesh Mishra, dean of the College of Engineering and professor in the Electrical and Computer Engineering Department, and Tyler Susko, an associate teaching professor in the Mechanical Engineering Department, for receiving Innovation Awards from Pacific Coast Business Times! 🎉

Click here to read more: engineering.ucsb.edu/news/innovat... #UCSB #COE #UCSBEngineers

Happy #ScienceAppreciationDay to those who celebrate (everyone should celebrate). Here’s what #UCSB researchers are working on:

#UCSB researchers are also working on this: #ScienceAppreciationDay

Despite its deep roots in American history, African American English has been overlooked in higher education. That’s changing thanks to scholars like #UCSB’s Michelle Petty, who co-authored an illuminating paper calling for Black linguistic justice in college classrooms news.ucsb.edu/2025/021761/...

The next ice age is expected in 10,000 years, a new study by an international team including #UCSB predicts. However, human-driven emissions have already diverted the climate from its natural course 🌍❄️ news.ucsb.edu/2025/021777/...

Innovators and the firsts in their field from #UCSB 🏆

This #WomensHistoryMonth we’re celebrating firsts: the first Women’s Center at UC Santa Barbara—founded 50 years ago—along with UCSB alums, faculty and students who are innovators, making groundbreaking discoveries or the first in their fields and paving the way for the next generation.

#UCSB's Jesse Landesman hopes to encourage other women to gain the confidence to pursue research and graduate education — "and to realize their potential as dirt-loving scientists."

This #UCSB alum—who earned her master’s degree studying carbon sequestration— researches how elevated soil salinity takes its toll on avocados in California, home to 95% of the nation’s commercial harvest 🔬🥑 Full story: magazine.ucsb.edu/fall-winter-...

With California considering proposed changes to its groundbreaking network of marine protected areas (MPAs), open-source marine spatial planning tool SeaSketch California could be shaping the future of ocean protection. It was developed in the lab of a #UCSB researcher: news.ucsb.edu/2025/021790/...

#UCSB anthropologists Amber VanDerwarker and Doug Kennett have uncovered key insights into the history of avocado domestication dating back 11,000 years 🥑 They also made an unexpected discovery: avocados were being farmed even before maize. Full story: news.ucsb.edu/2025/021782/...

🔋 Materials associate professor Raphaële Clément is part of the Aqueous Battery Consortium, working to develop new battery technologies to decarbonize transportation and incorporate clean energy into the electricity grid. Read more: engineering.ucsb.edu/news/ucsb-pr...

🚀 Emilie Dressaire of the Department of Mechanical Engineering sent experiments to the International Space Station to study treatments for respiratory distress syndrome. Read more: engineering.ucsb.edu/sites/defaul...

At UCSB's College of Engineering, our 38 women faculty members are making tremendous contributions to the field, from batteries to desalination to anaerobes. During National Women’s History month, get to know a few recently profiled engineers🔬👩‍🔬 engineering.ucsb.edu/womens-histo... #UCSB #COE

Researchers at #UCSB are opening new possibilities for sensing, precision timekeeping, quantum computing and fundamental science measurements in cold atom quantum experiments. news.ucsb.edu/2025/021786/...

Join us for the #WiDS Panel on Women’s Brain Health!🧠 Why is sex-specific data crucial? From ADHD under-diagnosis to healthcare gaps, we’ll dive in. 📅 March 12 | 8 AM PT 📍 YouTube -link in comment With @amykooz.bsky.social @ariannazuanazzi.bsky.social E. Rosenthal T. Silk R. Neuhaus & N. Williams

This all started last year with a simple question: who first applied sparse coding to neural representations for more interpretable codes? That question led us to uncover links between identifiability, compressed sensing, and interpretability—a story that was too good not to tell. 🧩

We’re looking for feedback and especially criticism before sending this off to a journal. If you’re into neural representations, we’d love to hear your thoughts! 📝🔥 arxiv.org/abs/2503.01824

At the core: 1️⃣ Identifiability theory 2️⃣ Compressed sensing 3️⃣ Quantitative interpretability Our goal is a unified model for LRH, superposition, sparse coding, and AutoInterp—backed by theory and practical insights. 🧠🔍 arxiv.org/abs/2503.01824

New preprint!🚀 Decoding neural representations is a challenge in neuroscience & AI. 👉 Learn how identifiability theory, compressed sensing & interpretability research -w/ a dash of geometry- can help! @david-klindt.bsky.social @rpatrik96.bsky.social C. O'Neill H. Maurer @ninamiolane.bsky.social

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

I had an idea way back in college which I've long thought could be, in many ways, the ultimate BCI technology. What if instead of using electrodes, we used biological neurons embedded in electronics to communicate with the brain? Enter biohybrid neural interfaces: science.xyz/news/biohybr...

Our PI @mbeyeler.bsky.social has received the 2024-’25 Harold J. Plous Memorial Award by @ucsb.bsky.social, in recognition of his “outstanding contributions in research, teaching, and service.“ New article by @ucsbengineering.bsky.social: engineering.ucsb.edu/news/outstan...

“Seeing the future”: More media coverage about @mbeyeler.bsky.social winning the 2024-25 Harold J. Plous Memorial Award @ucsantabarbara.bsky.social news.ucsb.edu/2024/021709/...

Virtual Human Retina: A simulation platform designed for studying human retinal degeneration and optimizing stimulation strategies for retinal implants 👁️🧠🧪 doi.org/10.1016/j.br...

A monumental modeling effort by Tianruo Guo & Team! 🧠🧪 The paper stops short of simulating retinal remodeling but impressively replicates key markers of the degenerated retina, like hyperactivity and oscillations. A valuable framework for optimizing stimulation strategies of retinal implants!