Geometric Intelligence Lab
@geometric-intel.bsky.social
Research lab at UCSB Engineering revealing the geometric signatures of nature and artificial intelligence | PI: @ninamiolane.bsky.social
🎉Congratulations to Guillermo Bernárdez Gil! Thrilled to share that our postdoc, Guille, has been awarded the 2026 Extraordinary Doctoral Award by the Universitat Politècnica de Catalunya (UPC). Congrats, Guille, so proud to have you on our team👏 🔗https://tinyurl.com/43hbr9t3
Huge congrats to the team. Nima is now an Associate Professor at Texas A&M, and Steve Bako is at Aurora Innovation. Proud to see our research community shaping the future of graphics, 10+ years on!🎓🖥️
It was the first ML approach to Monte Carlo denoising and the ideas still power nearly every modern denoiser today. This is what the SIGGRAPH 2026 Test-of-Time Award honors: research whose impact only grows with age. 🕰️
🏆Congrats to Prof. Pradeep Sen and former PhD student Nima Kalantari who were just awarded the SIGGRAPH Test-of-Time Award for their 2015 paper that transformed computer graphics rendering! Read more here👇 tinyurl.com/mvh569zx @ucsbengineering.bsky.social @ucsantabarbara.bsky.social
Read more: www.nature.com/articles/s42... @geometric-intel.bsky.social @neurreps.bsky.social @ai-ucsb.bsky.social @ucsbece.bsky.social @ucsbengineering.bsky.social
A unifying framework from neural superposition to sparse interpretable codes - Nature Machine Intelligence
Kindt et al. present a unifying framework for superposition in neural networks. Their three-step approach clarifies how latent features can be identified, disentangled and assessed.
nature.com
The concept of superposition has motivated over three decades of work across different communities. It states that neural networks encode features by overlaying multiple concepts ('elephant', 'ball', 'pink') linearly within the same set of neurons. We ask: how can we recover these concepts?
Our review on superposition in AI & brains is published in @nature.com #Machine #Intelligence 🌐 Neural networks encode concepts in superposition. We can recover them in 3 steps: identifiability, compressed sensing, interpretability. W/ @david-klindt.bsky.social O'Neil Reizinger & Maurer 🌟
This just in: we are hiring a Lab Manager😼 Looking for a detail-oriented and organized UC Santa Barbara undergraduate to oversee administrative projects, event coordination, social media presence, and more in the lab.⚛️ Apply here👇 tinyurl.com/5bwmcmkw
Log in or sign up | Handshake
tinyurl.com
🔵⚡Big feature in @cnn.com this week on our very own Prof. Shuji Nakamura (Materials & ECE). The man who lit up the world with blue LEDs, and now wants to power it too. 🔗https://tinyurl.com/msm4h9bf @ucsantabarbara.bsky.social @ucsbengineering.bsky.social
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
His work delivers algorithms that pull clean signals out of terabytes of messy brain-imaging data, along with mathematical frameworks that explain how stable thoughts and behaviors emerge from the seemingly chaotic activity of millions of neurons. 🧠
Awarded every two years to *one* outstanding early-career researcher *worldwide*, the DiPrima Prize recognizes Fatih's research building a bridge between mathematics and neuroscience.🌉
🎉 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
Join @ninamiolane.bsky.social as she discuss with Claire Isabel Webb the hidden shapes and structure inside high-dimensional neural data and their connection to understanding the brain. 🧠
Nina Miolane@ninamiolane.bsky.social · 2mo ago🧠 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
What an incredible season of Long Now Talks! We heard from @ninamiolane.bsky.social on the geometry of consciousness, @ericries.bsky.social on incorruptibility, @bayoakomolafe.bsky.social on new time paradigms, @indyjohar.bsky.social on planetary consciousness + more
🧠 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
The Long Now Foundation@longnow.org · 2mo agoCould there be a universal geometry of intelligence? @ninamiolane.bsky.social proposes answers in her Long Now Talk with @berggruen.org's Claire Isabel Webb.
Could there be a universal geometry of intelligence? @ninamiolane.bsky.social proposes answers in her Long Now Talk with @berggruen.org's Claire Isabel Webb.
This award, supported by ICMBE2026, recognizes exceptional contributions to molecular beam epitaxy by researchers under 40. Prof. Ahmadi is a deserving honoree and we couldn't be prouder. 💛💙 #UCSB #MBE #WideBandgap #PowerElectronics #QuantumDevices #MaterialsScience
🏆Congratulations to Prof. Elaheh Ahmadi, recipient of the 2026 Young Investigator MBE Award from the International MBE Advisory Committee! Her research on novel ultra wide bandgap devices is pushing the boundaries of high power, high frequency, and quantum applications.🔬⚡
Way to go Daniel!! 😼
Daniel Holmberg@dholmberg.bsky.social · 2mo agoThe ocean is inherently chaotic, yet existing data-driven ocean models produce deterministic forecasts. In our new preprint, we introduce Njord, a probabilistic graph neural network for ensemble ocean forecasting. Link: arxiv.org/abs/2605.15470 A couple highlights below 🧵
• Lastly, animation of an extra long sea ice concentration rollout over the spring of 2024 for the Baltic Sea, with reanalysis atmospheric forcing. The regional model remains surprisingly stable while only trained with 2 autoregressive steps.
• Sea ice is predicted alongside other physical state variables. Smooth invertible activation functions together with a binary density channel keep ice variables within realistic bounds.
• K-means cluster meshes. Latitude weighted spherical K-means produces a mesh that conforms better to ocean grids by construction compared to previously used quadrilateral or icosahedral meshes.
• Latent-variable graph neural network. A per-step Gaussian latent on the coarsest mesh level injects stochasticity into a hierarchical encode-process-decode backbone. The model only requires one forward pass per ensemble member.
• Njord is trained globally at 0.25° and on the Baltic Sea at 2km resolution. In the regional setting Njord conditions on boundary data from an independent global ocean model, where previous emulators either lack boundary forcing or depend on the very system they aim to replace.
🏥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
This paper was published last week in Optica, and spin-out company Pacific Optica is now bringing this tech to labs worldwide.🌎 @ucsbengineering.bsky.social @ucsantabarbara.bsky.social
"…we want to see hundreds of neurons, thousands of neurons, with the ultimate goal of being able to look at how individual neurons work together across the entire brain." – Postdoc Che-Hang Yu
