Jeremy Wayland
@jeremy_wayland
Followers
54
Following
168
Media
0
Statuses
26
4th year PhD Candidate at @HelmholtzMunich and @TU_Muenchen working in the AIDOS Lab.
Munich
Joined August 2022
Want to generate point clouds? Our (@ErnstRoell) #NeurIPS2025 paper shows a topology-driven method that is fast, simple, and high-quality. 🔥 1/n
1
11
28
😇Hijacking this great thread to talk about a potential way to _identify_ problems with existing benchmarking datasets (also to appear in ICML 2025): https://t.co/RvTgQMW9ZP TL;DR: We look at how "graphical" graph benchmarking datasets are. Spoiler: less than you'd hope for!
📣 Our spicy ICML 2025 position paper: “Graph Learning Will Lose Relevance Due To Poor Benchmarks”. Graph learning is less trendy in the ML world than it was in 2020-2022. We believe the problem is in poor benchmarks that hold the field back - and suggest ways to fix it! 🧵1/10
1
10
32
Our AIDOS Lab website has been fully revamped, thanks to a massive team effort as part of a very fun retreat in #Bern: https://t.co/y35fnfks05 Check out our research directions and some of the things we have been up to these days! #Academia #MachineLearning
6
3
48
Amazing week - Understanding Virtual Nodes accepted to ICLR: https://t.co/T0CdQ3VLGk - Hit my first 180 🎯 - Passed my PhD without corrections Thank you to everyone involved!
openreview.net
While message passing neural networks (MPNNs) have convincing success in a range of applications, they exhibit limitations such as the oversquashing problem and their inability to capture...
5
8
67
Hi!👋Emily Simons here, @FulbrightPrgrm Student Researcher with @HelmholtzMunich's AIDOS Lab. Happy to be sharing my first contribution to AIDOS in this 🧵. Say hiya to SCOTT, the perfect holiday (software) package🎁for the #curvature and #graph enthusiast in your life. 🧵1/n
1
4
12
📢 Exciting News! Our paper, “Bayesian Computation Meets Topology,” has just been published in TMLR! 🎉 👉 https://t.co/QKPZgupnyb 👈 Here’s a deep dive into how #topology and #bayes(ian) computation come together to enhance parameter inference: 📌 Why Topology? Topology
openreview.net
Computational topology recently started to emerge as a novel paradigm for characterising the ‘shape’ of high-dimensional data, leading to powerful algorithms in (un)supervised representation...
0
20
110
(1/6) I am thrilled to share my latest research from my visit to @HelmholtzMunich in the #AIDOS lab led by @Pseudomanifold! 🚀 We introduced Redundant Blocks Approximation (RBA)—a straightforward method to reduce model size & complexity while maintaining good performance📈🤖
1
10
61
Friends, as the saying approximately goes: "Fortune favours the bald" 👴 👉 My proposal "HOLES: Higher-Order Learning of Essential Structures with Geometry and Topology" was successfully funded with a 1.5M € @ERC_Research Starting Grant! 👈 🤯🤯🤯 This will allow me to pursue
39
23
271
Friends, I am beyond happy! I'm starting a new position as Full Professor of #MachineLearning at the University of Fribourg @unifr 🇨🇭! With #SwissAI and many other initiatives, I am taking my research at the intersection of #geometry, #topology, and #MachineLearning to a new
80
39
548
New blog post: ᴅᴏɪɴɢ ᴍʟ ʀᴇꜱᴇᴀʀᴄʜ: ɢᴀᴛᴇꜱ ᴏᴘᴇɴ, ᴄᴏᴍᴇ ᴏɴ ɪɴ! Intended as an invitation to #MachineLearning, in particular for researchers coming from #mathematics. (Prompted by recent discussions in a @dagstuhl seminar!) https://t.co/UZlCkc2KHn
bastian.rieck.me
2
9
58
I am thrilled to announce HistoGPT, a vision language foundation model that generates highly accurate pathology reports from gigapixel whole slide images. medRxiv: https://t.co/63e8qmNRZj GitHub: https://t.co/H8tLifsqtA Hugging Face: https://t.co/7YrFLZ97mQ
2
44
153
We hope that this paves the path towards new, highly-efficient topology-driven methods. 📜 https://t.co/GXGk2bHYfk 💻 https://t.co/IZpI5C9qHu As a PI, I'm very proud to see @ErnstRoell's excellent work paying off! 😊 🧵5/5
openreview.net
The _Euler Characteristic Transform_ (ECT) is a powerful invariant, combining geometrical and topological characteristics of shapes and graphs. However, the ECT was hitherto unable to learn...
0
5
15
Exciting news! CHOC's (@chocchildrens) Healthcare Data Science Conference is now open for registration and is a must-attend event for those interested in the intersection of data science and healthcare. For more information and to register, visit https://t.co/7W4yJ1FBN2.
choc.org
Join global experts at the International Pediatric Data Science Roundtable on April 29-30, 2026 to advance data science in child healthcare.
0
2
6
🎉 Wrapping up 2023 with... 1. ...a 'Deep Learning Grand Slam' - ICLR: Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework ( https://t.co/aZaYGcKXz9) We (@CorinnaCoupette, S. Dalleiger, YT) define notions of hypergraph #curvature & show their applications. 🧵1/n
3
36
168
My first first-author journal paper now featuring in The Guardian! Great collaboration with @Sarkar_Lab @RikSarkarNet @BioMedAI_CDT @InfAtEd @FoodSciLeeds 🗞️@guardianscience : https://t.co/VGwMzcAWeQ ➡️ @SciReports :
theguardian.com
Analysis of 3D images reveals the organ’s bumps and grooves are as personal as fingerprints
1
3
21
Have you ever wondered how topological data analysis can be applied to the analysis of neural networks? I'm excited to share our newest survey on TDA for deep learning, offering an in-depth look at this intriguing question. 🧵 https://t.co/bzfkftB37f
3
43
189
Sadly also can't attend #NeurIPS2023 this year to present this work but please see @JeremyWayland at the poster session! Also please feel free to reach out to me if you have any questions/just want to chat about graphs in general so I have less fomo 😃
I won't be at #NeurIPS2023 (👶) but can highly recommend visiting our (@JoshSouthern13 @JeremyWayland @mmbronstein) work! TL;DR: #Curvature + #Topology = Great for Generative Model Eval! ➡️Poster #539 @ Session 3 (Dec 13) 📜 https://t.co/ojC5kiX6mb Some #FOMO starting now!🫠
0
2
14
I won't be at #NeurIPS2023 (👶) but can highly recommend visiting our (@JoshSouthern13 @JeremyWayland @mmbronstein) work! TL;DR: #Curvature + #Topology = Great for Generative Model Eval! ➡️Poster #539 @ Session 3 (Dec 13) 📜 https://t.co/ojC5kiX6mb Some #FOMO starting now!🫠
openreview.net
Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient...
2
4
60
Interested in #curvature on #graphs? 🚀 Check out our (@JoshSouthern13, @jeremy_wayland, @mmbronstein) #NeurIPS2023 paper ‘Curvature Filtrations for Graph Generative Model Evaluation’ 📜: https://t.co/9RmViZ7aPc 💻: https://t.co/QDZmZDSNbD
#topology #geometry 🧵1/n
1
18
90