Profile avatar
mniepert.bsky.social
Professor @ University of Stuttgart, Scientific Advisor @ NEC Labs, GraphML, geometric deep learning, ML for Science and Simulations. Formerly @IUBloomington and @uwcse
8 posts 1,172 followers 355 following
Regular Contributor
Posts 22 Comments 7

The slides for my lectures on (Bayesian) Active Learning, Information Theory, and Uncertainty are online now 🥳 They cover quite a bit from basic information theory to some recent papers: blackhc.github.io/balitu/ and I'll try to add proper course notes over time 🤗

submitted 72 days ago • 4 comments

Want to turn your state-of-the-art diffusion models into ultra-fast few-step generators? 🚀 Learn how to optimize your time discretization strategy—in just ~10 minutes! ⏳✨ Check out how it's done in our Oral paper at ICLR 2025 👇

submitted 14 days ago • 0 comments

Welcome to our Bluesky account! 🦋 We're excited to announce ComBayNS workshop: Combining Bayesian & Neural Approaches for Structured Data 🌐 Submit your paper and join us in Rome for #IJCNN2025! 🇮🇹 📅 Papers Due: March 20th, 2025 📜 Webpage: combayns2025.github.io

submitted 14 days ago • 0 comments

🚀 Exciting news! Our paper "Learning to Discretize Diffusion ODEs" has been accepted as an Oral at #ICLR2025! 🎉 [1/n] We propose LD3, a lightweight framework that learns the optimal time discretization for sampling from pre-trained Diffusion Probabilistic Models (DPMs).

submitted 14 days ago • 1 comment

Very excited to announce the Neurosymbolic Generative Models special track at NeSy 2025! Looking forward to all your submissions!

submitted 69 days ago • 0 comments

arxiv.org/abs/2412.11569, a very relevant effort!

submitted 72 days ago • 2 comments

Catch my poster tomorrow at the NeurIPS MLSB Workshop! We present a simple (yet effective 😁) multimodal Transformer for molecules, supporting multiple 3D conformations & showing promise for transfer learning. Interested in molecular representation learning? Let’s chat 👋!

submitted 74 days ago • 0 comments

We will run out of data for pretraining and see diminishing returns. In many application domains such as in the sciences we also have to be very careful on what data we pretrain to be effective. It is important to adaptively generate new data from physical simulators. Excited about the work below

submitted 75 days ago • 0 comments

I'll present our paper in the afternoon poster session at 4:30pm - 7:30 pm in East Exhibit Hall A-C, poster 3304!

submitted 77 days ago • 0 comments

Neural surrogates can accelerate PDE solving but need expensive ground-truth training data. Can we reduce the training data size with active learning (AL)? In our NeurIPS D3S3 poster, we introduce AL4PDE, an extensible AL benchmark for autoregressive neural PDE solvers. 🧵

submitted 78 days ago • 1 comment

Join us today at #NeurIPS2024 for our poster presentation: Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing 🗓️ When: Wed, Dec 11, 11 a.m. – 2 p.m. PST 📍 Where: East Exhibit Hall A-C, Poster #4107 #MachineLearning #InteratomicPotentials #Equivariance #GraphNeuralNetworks

submitted 78 days ago • 0 comments

"Transferability of atom-based neural networks" authored by @januseriksen.bsky.social (thanks for publishing with us, amazing work!) is now out as part of the #QuantumChemistry and #ArtificialIntelligence focus collection #MachineLearningScienceandTechnology. Link: iopscience.iop.org/article/10.1...

submitted 79 days ago • 0 comments

1/6 We're excited to share our #NeurIPS2024 paper: Probabilistic Graph Rewiring via Virtual Nodes! It addresses key challenges in GNNs, such as over-squashing and under-reaching, while reducing reliance on heuristic rewiring. w/ Chendi Qian, @christophermorris.bsky.social @mniepert.bsky.social 🧵

submitted 82 days ago • 1 comment

New #compchem paper out in MLST. We study the transferability of both invariant and equivariant neural networks when training these either exclusively on total molecular energies or in combination with data from different atomic partitioning schemes: iopscience.iop.org/article/10.1...

submitted 82 days ago • 0 comments

You should take a look at this if you want to know how to use Cartesian (instead of spherical) tensors for building equivariant MLIPs.

submitted 83 days ago • 0 comments

📣 Can we go beyond state-of-the-art message-passing models based on spherical tensors such as #MACE and #NequIP? Our #NeurIPS2024 paper explores higher-rank irreducible Cartesian tensors to design equivariant #MLIPs. Paper: arxiv.org/abs/2405.14253 Code: github.com/nec-research...

submitted 83 days ago • 2 comments

@ropeharz.bsky.social forced me to do this starter pack on #tractable #probabilistic modeling and #reasoning in #AI and #ML please write below if you want to be added (and sorry if I did not find you from the beginning). go.bsky.app/DhVNyz5

submitted 90 days ago • 12 comments

Amazing opportunity for #Neurosymbolic folks! 🚨🚨🚨 We are looking for a Tenure Track Prof for the 🇦🇹 #FWF Cluster of Excellence Bilateral AI (think #NeSy ++) www.bilateral-ai.net A nice starting pack for fully funded PhDs is included. jobs.tugraz.at/en/jobs/226f...

submitted 91 days ago • 3 comments

I haven’t read it carefully, but +1 to works like the one below. It mentions learning artifacts from discreetness. We saw some things like that in this paper, where bad integration of the true Hamiltonian did worse than a learned model (that absorbed artifacts). arxiv.org/abs/1909.12790

submitted 93 days ago • 0 comments

We've all been there 🤓 #DeepLearning

submitted 95 days ago • 3 comments

For those who missed this post on the-network-that-is-not-to-be-named, I made public my "secrets" for writing a good CVPR paper (or any scientific paper). I've compiled these tips of many years. It's long but hopefully it helps people write better papers. perceiving-systems.blog/en/post/writ...

submitted 99 days ago • 4 comments

Can deep learning finally compete with boosted trees on tabular data? 🌲 In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters. Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵

submitted 101 days ago • 1 comment