Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 13/09/2026For a vibe-coded universe, the sunsets are pretty marvelous, I'll grant you that. 030
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 01/09/2026The Road goes ever on and on Down from the door where it began. Now far ahead the Road has gone, And I must follow, if I can, Pursuing it with eager feet, Until it joins some larger way Where many paths and errands meet. And whither then? I cannot say. #Switzerland 010
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 26/05/2026Gladiator vibes...good evening, y'all! 000
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 26/05/2026Some respite before the heat starts again. Good morning, everyone! 020
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 19/05/2026The Boston TAG Party (August 18–20) is open for submissions! openreview.net/group?id=TAG... Submit your work in topology, algebra, and geometry. 040
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 30/04/2026Walking to the office always gives me Lord of the Rings vibes. #Fribourg #Freiburg 2121
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025And it just works! Our pooling methods perform well across tasks and… 🏆 …reach top classification and regression performance. 🔥 …retain this robust performance across pooling ratios. ✨ …preserve graph structure and spectral properties 🧵4/n 111
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025But…how? 🔍 We contract the most redundant edges that are least relevant for the graph’s structural diversity as measured by the magnitude or spread of a graph. 🧵3/n 111
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025Why do we need structure-aware pooling, anyway? 🔮Our methods, MagEdgePool and SpreadEdgePool, faithfully preserve the original graphs’ geometry. Alternative pooling layers destroy graph structure to varying extents. 🧵2/n 121
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 11/11/2025Big graph, little compute? In our #NeurIPS2025 paper we propose geometry-aware edge-contraction-based pooling methods for GNNs. Our methods preserve graph structure, make interpretable pooling choices, and ensure robust performance at downstream tasks. 🧵1/n 1134
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 03/11/2025As a rule of thumb, we observe that when the mean LID drops and stabilizes, performance is typically improving. By contrast, when the mean LID drops and rises again, this is a warning for overfitting. 🧵3/n 110
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 03/11/2025It's epoch 50. Do you know whether your LLM is grokking? In our #NeurIPS2025 paper "Less is More: Local Intrinsic Dimensions of Contextual Language Models," we study how the local intrinsic dimension (LID) of embeddings changes during training and fine-tuning. #research 🧵1/n 152
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 29/10/2025It's amazingly fast (< 𝟏𝐡 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐟𝐮𝐥𝐥 𝐩𝐢𝐩𝐞𝐥𝐢𝐧𝐞, 𝐭𝐫𝐚𝐢𝐧𝐞𝐝 𝐨𝐧 𝐚 𝐠𝐚𝐦𝐢𝐧𝐠 𝐥𝐚𝐩𝐭𝐨𝐩) and high-quality. Another Topological Deep Learning success story, coming soon to #NeurIPS2025! 🖥️ github.com/aidos-lab/in... 📜 arxiv.org/pdf/2410.18987 4/n 151
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 29/10/2025What we gain is a 𝐬𝐭𝐚𝐛𝐥𝐞 and 𝐞𝐱𝐩𝐫𝐞𝐬𝐬𝐢𝐯𝐞 latent space that permits simple interpolation. 3/n 130
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 29/10/2025Want to generate point clouds? Our (w/ Ernst Röell) #NeurIPS2025 paper shows a topology-driven method that is fast, simple, and high-quality. 🔥 1/n 1174
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 24/08/2025New blog post: Consciousness Is Overrated Anyway (for AI) In which I, somewhat coherently, try to contribute to the whole "Is AI Conscious" debate. 🔗 bastian.rieck.me/blog/2025/co... #AI #MachineLearning 141
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/08/2025Geometry and topology help us see structure and shape, providing a principled way to imbue models with such concepts… …and it's not a niche perspective, thanks to a lot of great work by the community! 🧵3/5 110
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/08/2025We all know the dogma: "Given enough data, the model will learn everything." But as LLMs hit diminishing returns (bough with even more GPUs!), this belief is being challenged. I'm not the only one who posits that inductive biases remain important. 🧵2/5 120
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/08/2025🎥 Shapes, Spaces, Simplices, and Structure: Geometry, Topology & Machine Learning "What if the answer to some problems in graph learning is not more, but better structure?" This is the central premise of my talk @logml.bsky.social and @unireps.bsky.social. 🧵1/5 191
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 06/08/2025"SAFE TY FIRST" Kerning. Once you know about it, your enjoyment of public signage will be ruined forever. en.wikipedia.org/wiki/Kerning 010
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 01/08/2025🇨🇭 Happy #SwissNationalDay! It's already a year since I started my new position @unifr.bsky.social and I'v had the good fortune to be living here since 2018. Thanks for everything, Switzerland! 🙏 Here's to the future! 🚀 1130
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 22/07/2025#MachineLearning loves data. #Topology loves shape. Let's bring them together! 👉The Euler Characteristic Transform (ECT) bridges both worlds, as I outline in a recent article in the Notices of the @amermathsoc.bsky.social Engage! 🧵1/n 1105
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 29/04/2025Thoughts on current events. 070
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 10/04/2025A candidate for the most audacious correction ever. Replacing a large chunk of the bibliography with "relevant" citations, plus an example of "vegetative electron microscopy." What's going on here? #AcademicSky Source: www.mdpi.com/1996-1944/17... 150
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 01/03/2025Our AIDOS Lab website has been fully revamped, thanks to a massive team effort as part of a very fun retreat in #Bern: aidos.group Check out our research directions and some of the things we have been up to these days! #Academia #MachineLearning 1101
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 24/02/2025📣 ATMCS 11 will be in beautiful Bozeman, MT. We are still soliciting 3-page extended abstracts (with subsequent full-paper proceedings in La Matematica). Still open for submissions about applied #topology (broadly interpreted)! Check out the CfP here: 👉 comptag.github.io/atmcs11/call... 👈 071
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/02/2025🔥 Friends, I finally collected them all. As of last week, I am finally tenured. 🔥 Thanks to everyone who supported me, in particular my great team (aidos.group), my equally great collaborators, and everyone else who brought their offerings to the fickle fates of academia! #Academia #Tenure 5382
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 13/01/2025Back from my first JMM (@jointmath.bsky.social). I enjoyed so many interesting talks and discussions. One highlight was a working (!) Enigma exhibit. Plus: Seattle is a beaut! 0110
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 03/01/2025Happy New Year, everyone! There's always a nice #bluesky above the clouds! 1200
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 29/12/2024This is what my OpenReview notifications look like as an AC. (I read through all the e-mails of course but have to acknowledge them in the web interface as well). Happy Holidays and best of luck for your papers! @iclr-conf.bsky.social 0140
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 20/11/2024Hey friends! I am interested in #geometry, #topology, and #MachineLearning. Silent lurker for some time, but now with the recent influx, I'd love to engage more. If you followed me from the 'other place' but I did not follow you back, let me know! The notifications here are sometimes a bit much... 2392
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 08/09/2023My dog is silently judging me while I'm writing bad code. 010
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 07/09/2023Just crossed my mind while reading Bredon... 020
Bastian Grossenbacher-Rieck @pseudomanifold.topology.rocks · 05/09/2023A bad habit I try to get rid of when writing papers is the overuse of the word 'intuitively.' 240