Jan Stühmer @ICML
@janstuehmer.bsky.social
ML for Science, Interpretability & GNNs. Jun.-Prof. @ KIT. ML-Group @ Heidelberg Institute for Theoretical Studies. Previously Samsung AI, Microsoft Research, MIT-CSAIL, TUM & Caltech. Opinions and typos are my own.
4/4 We believe that our proposed Clifford Frame Attention can also be suitable for other protein structure related machine learning models, as a drop-in replacement for Alphafold's IPA.
January 6, 2025 at 3:40 PM
4/4 We believe that our proposed Clifford Frame Attention can also be suitable for other protein structure related machine learning models, as a drop-in replacement for Alphafold's IPA.
3/4 The proposed model achieves high designability, diversity and novelty, while also following the statistical distribution of secondary structure elements found in naturally occurring proteins.
January 6, 2025 at 3:40 PM
3/4 The proposed model achieves high designability, diversity and novelty, while also following the statistical distribution of secondary structure elements found in naturally occurring proteins.
2/4 We introduce a generative model for protein backbone design that utilizes geometric products and higher order message passing and propose Clifford Frame Attention (CFA), an extension of AlphaFold's invariant point attention (IPA).
January 6, 2025 at 3:40 PM
2/4 We introduce a generative model for protein backbone design that utilizes geometric products and higher order message passing and propose Clifford Frame Attention (CFA), an extension of AlphaFold's invariant point attention (IPA).
January 6, 2025 at 2:44 PM
Generative flow matching model for highly designable proteins:
Simon Wagner & Leif Seute et al., Generating Highly Designable Proteins with Geometric Algebra Flow Matching, Neurips 2024
arxiv.org/abs/2411.05238
Simon Wagner & Leif Seute et al., Generating Highly Designable Proteins with Geometric Algebra Flow Matching, Neurips 2024
arxiv.org/abs/2411.05238
Generating Highly Designable Proteins with Geometric Algebra Flow Matching
We introduce a generative model for protein backbone design utilizing geometric products and higher order message passing. In particular, we propose Clifford Frame Attention (CFA), an extension of the...
arxiv.org
January 5, 2025 at 4:28 PM
Generative flow matching model for highly designable proteins:
Simon Wagner & Leif Seute et al., Generating Highly Designable Proteins with Geometric Algebra Flow Matching, Neurips 2024
arxiv.org/abs/2411.05238
Simon Wagner & Leif Seute et al., Generating Highly Designable Proteins with Geometric Algebra Flow Matching, Neurips 2024
arxiv.org/abs/2411.05238
Calibrated predictions with GNNs:
Moritz Feik et al., Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts, Earth System Modeling Workshop @ ICML2024,
arxiv.org/abs/2407.11050
Moritz Feik et al., Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts, Earth System Modeling Workshop @ ICML2024,
arxiv.org/abs/2407.11050
Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts
Ensemble forecasts from numerical weather prediction models show systematic errors that require correction via post-processing. While there has been substantial progress in flexible neural network-bas...
arxiv.org
January 5, 2025 at 4:28 PM
Calibrated predictions with GNNs:
Moritz Feik et al., Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts, Earth System Modeling Workshop @ ICML2024,
arxiv.org/abs/2407.11050
Moritz Feik et al., Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts, Earth System Modeling Workshop @ ICML2024,
arxiv.org/abs/2407.11050
Learnable parameterized force field models:
Leif Seute et al., Grappa - A Machine Learned Molecular Mechanics Force Field, AI for Science Workshop @ ICML2024 arxiv.org/abs/2404.00050
Leif Seute et al., Grappa - A Machine Learned Molecular Mechanics Force Field, AI for Science Workshop @ ICML2024 arxiv.org/abs/2404.00050
Grappa -- A Machine Learned Molecular Mechanics Force Field
Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted the tension between co...
arxiv.org
January 5, 2025 at 3:49 PM
Learnable parameterized force field models:
Leif Seute et al., Grappa - A Machine Learned Molecular Mechanics Force Field, AI for Science Workshop @ ICML2024 arxiv.org/abs/2404.00050
Leif Seute et al., Grappa - A Machine Learned Molecular Mechanics Force Field, AI for Science Workshop @ ICML2024 arxiv.org/abs/2404.00050