Jan Stühmer @ICML

Please consider making a donation to support students who want to attend the annual gathering of the African AI community. (They are currently about 1/3 towards their financial goal...)

We are hiring a postdoc/research associate at @ITUkbh and @mitibmlab (funded by the @ClimateChangeAI grant) to work at the intersection of deep learning and OR towards developing data-driven methods for making the last-mile logistics, greener. Apply here: greenlastmile.ai/jobs

I'm now on Bluesky 🦋 You can find me at bsky.app/profile/janstu… I have created a Machine Learning and AI for Science starterpack: go.bsky.app/FPgU6Pt Let me know if you would like to be added. #AI4Science #MachineLearning #BlueSky

I have created a Bluesky starter pack for AI for Science. Let me know if you would like to be added. go.bsky.app/FPgU6Pt

Super excited to announce our #neurips2024 paper, "Generating Highly Designable Proteins with Geometric Algebra Flow Matching". Amazing cooperation with Simon Wagner, @LeifSeute, Seva Viliuga @_ncyxx, Nicolas Wolf, and Frauke Graeter @graeter_mbm linkedin.com/posts/jan-stuh…

New paper "Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts", with Moritz Feik and @JanStuehmer available at doi.org/10.5445/IR/100…, accepted at the ICML 2024 Workshop on Machine Learning for Earth System Modeling.

Tipp für Raum #Heidelberg: 'ChatGPT & Co" - über große Sprachmodelle und ihre Auswirkungen auf uns alle spricht unser Journalist in Residence @anilananth am 5. Juli um 19:00 in der MAINS (on-site, kein Streaming). Mehr dazu hier: ow.ly/noxk50P1bhI @HLForum @ktstiftung

🎉🌍😍 I'm thrilled to announce that I'll be attending #ICLR2023 in Rwanda from 1st-5th May to present my paper - Amortised Invariance Learning for Contrastive Self-Supervision. This is my first PhD paper and first in-person conference, so I'm super excited to be a part of it!

I'm hiring PhD students/postdocs with strong background in machine learning. Core topics of the research group include: • Geometric Deep Learning and Graph-ML for Molecule Generation and Molecular Docking • Interpretability • Causal Inference • Learning Theory #NeurIPS2022

The new #Machinelearning and #ArtificialIntelligence group at @HITStudies is now offering #phdpositions - apply here: bit.ly/3Cs5R9J @JanStuehmer #DeepLearning #variational #inference #learningtheory

We ended the first session with a talk from Jan Stühmer about machine learning approaches, through which he sometimes helps life scientists too!

Check out our paper HyperInvariances: Amortizing Invariance Learning (arxiv.org/pdf/2207.08304…) provides an interesting new avenue to learn invariances for diverse downstream tasks. Excited to present it at the SCIS Workshop on 22/07 at ICML 2022! #ICML2022 @henrygouk @tmh31

Is few-shot meta-learning successful for general modalities? Find out how well your favourite meta-learner does in few-shot audio tasks in our new benchmark "MetaAudio"! cheggan.github.io/posts/2022/04/…