Bastian Grossenbacher-Rieck

Kareem Carr standing outside Harvard School of Public Health moments after his successful PhD defense. He is smiling, dressed in a dark-patterned sport coat and dress pants, leaning casually against a railing. There is a bright red sign over his right shoulder that reads “Harvard T.H. Chan School of Public Health”.

Happy to announce I just defended my dissertation at Harvard and I’m now a PhD.

Funnily enough, there is a Freiburg in Germany and a Freiburg (Fribourg) in Switzerland 🤣

The Matterhorn

🇨🇭 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! 🚀

While you are waiting for your #NeurIPS reviewers, you might enjoy this tongue-in-cheek blog post I wrote:

The Missing Screwtape Letters from Academia
bastian.rieck.me/blog/2023/sc...

(With apologies to C.S. Lewis)

We grow better and stronger: a few inspiring visits between Mila and Helmholtz Munich:

1. read below on what a few week stays at Mila brought to Irene and Gab, PhD students from Benjamin Schubert and Maria Colome Tatché 's groups @HelmholtzMunich […]

[Original post on wisskomm.social]

Awwww 😊🫣😊🫣😊🥹

Looking very much forward to this event! Thanks for having me!

🔥 Mark your calendars for the next session of the @ellis.eu x UniReps Speaker Series!

🗓️ When: 31th July – 16:00 CEST
📍 Where: ethz.zoom.us/j/66426188160
🎙️ Speakers: Keynote by
@pseudomanifold.topology.rocks & Flash Talk by @florentinguth.bsky.social

Topology is cool, check it out!

If you like this kind of #TopologicalDeepLearning / #TDL research, also check out our research group's website:

👉 aidos.group

Thanks for reading!

🧵7/7

🙏Thanks to Emilie Purvine for inviting me to write this article. If you are looking for more awesome researchers to follow, don't miss
@elizabethmunch.bsky.social
and her wonderful article An Invitation to the Euler Characteristic Transform:
👉 tandfonline.com/doi/full/10....

🧵6/n

Try it out! Here's some code to get you started and additional resources to more awesome works:

💻 topology.rocks/ect
📜 ams.org/journals/not...

🧵5/n

What's more, the ECT can be made differentiable via simple sigmoid functions, for example. This opens up all kinds of interesting applications (loss terms, computational layers, you name it), all while remaining super fast and simple.

🧵4/n

How does it work? By looking at data from different directions, the ECT tracks topological information across different "slices" of your data.

🤯Taken together, the slices fully describe the shape, and in practice, a finite number of directions are sufficient!

🧵3/n

A priori, most models are not "shape-aware." The ECT encodes shapes in a way that is…

🔥 …blazingly fast
💉 …injective
🪨…robust

Plus, we can make it differentiable.

🧵2/n

An overview of the Euler Characteristic Transform, illustrated for a single Euler Characteristic Curve, i.e., the calculation of Euler characteristics along a single direction.

#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

a horse drawn carriage going through a grassy area ALT: a horse drawn carriage going through a grassy area

Join us on a (mathematical) journey to a shire - oops, HIGHER - standard and principled evaluation schema for our benchmark datasets. This is the reward of the RINGS framework.

📒 Blog: aidos.group/blog/rings/
📃 Paper: doi.org/10.48550/arX...
👩‍💻 Code: github.com/aidos-lab/ri...

✨Excited to be at ICML 2025 to share our new evaluation framework for graph-learning datasets, work with @dataspider.bsky.social, @jeremy-wayland.bsky.social, @pseudomanifold.topology.rocks

Curious about who shall pass, and who shall not?🤔
Enjoy nods to LoTR?🧝‍♀️
Check out our blog and paper below!

Next appointment: 31st July 2025 – 16:00 CEST on Zoom with 🔵Keynote: @pseudomanifold.topology.rocks (University of Fribourg) 🔴 @florentinguth.bsky.social (NYU & Flatiron)

Thanks a lot :-)

A great slide from a great talk by @pseudomanifold.topology.rocks at @logml.bsky.social

NeurReps Workshop - Call for Papers Call for Papers

📢 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...

🚨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

Very happy that Jiří Minarčík will join our research group at @cmu.edu, the Geometry Collective, as a Fulbright visiting scholar! 🥳

Jiří is a world expert in space curves, and one of the core contributors to Penrose (penrose.cs.cmu.edu). Check out his beautiful work here: minarcik.com

I am very happy to report that two of these students will join the AIDOS Lab @unifr.bsky.social to work on #geometry, #topology, and #MachineLearning 😊

Community Takes on the Future of Graph Learning On drifting goals, fresh frontiers, and a bittersweet lesson we are slowly learning

Check out this post from @ffabffrasca.bsky.social and the GLOW reading group on the future of graph learning!

I’ve also contributed and my main take is - its actually working and its an exciting moment to work on applications!

open.substack.com/pub/glowread...

You may read this chapter in the usual place:

geometricdeeplearning.com/book/ 📖

Any and all feedback / thoughts / questions on the content... words of encouragement for finishing this book (pretty please! 😇) warmly welcomed!

@mmbronstein.bsky.social @joanbruna.bsky.social @taco-cohen.bsky.social

The first draft 'G' chapter of the geometric deep learning book is live! 🚀

Alice enters the magical, branchy world of Graphs and GNNs 🕸️ (LLMs are there too!)

I've spent 7+ years studying, researching & talking about graphs -- This text is my best attempt at conveying everything i've learnt 💎

Today KellyMaggs @k311ym4gg5.bsky.social @math-mpicbg.bsky.social @mpicbg.bsky.social @tudresden.bsky.social will give talk on mathML research! @krishnaswamylab.bsky.social

new collaborator