"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges" by @mmbronstein.bsky.social, Joan Bruna, Taco Cohen, @petar-v.bsky.social
#geometricdeeplearning
#geometricdeeplearning
November 20, 2024 at 2:40 PM
"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges" by @mmbronstein.bsky.social, Joan Bruna, Taco Cohen, @petar-v.bsky.social
#geometricdeeplearning
#geometricdeeplearning
💻 GitHub: github.com/geometric-ke...
📄 JMLR Paper: www.jmlr.org/papers/v26/2...
#MachineLearning #GeometricDeepLearning #GaussianProcesses #Kernels #Graphs #Manifolds #JMLR #OpenSource
📄 JMLR Paper: www.jmlr.org/papers/v26/2...
#MachineLearning #GeometricDeepLearning #GaussianProcesses #Kernels #Graphs #Manifolds #JMLR #OpenSource
March 12, 2026 at 4:06 PM
💻 Code: github.com/PedrV/gnn-uq...
📄 Preprint: arxiv.org/abs/2605.22593
Co-authored w/ @pedrocvieira.bsky.social & Pedro Ribeiro.
#MachineLearning #GraphNeuralNetworks #DeepLearning #UncertaintyQuantification #GeometricDeepLearning
📄 Preprint: arxiv.org/abs/2605.22593
Co-authored w/ @pedrocvieira.bsky.social & Pedro Ribeiro.
#MachineLearning #GraphNeuralNetworks #DeepLearning #UncertaintyQuantification #GeometricDeepLearning
GitHub - PedrV/gnn-uq-inspector
Contribute to PedrV/gnn-uq-inspector development by creating an account on GitHub.
github.com
May 25, 2026 at 11:15 AM
💻 Code: github.com/PedrV/gnn-uq...
📄 Preprint: arxiv.org/abs/2605.22593
Co-authored w/ @pedrocvieira.bsky.social & Pedro Ribeiro.
#MachineLearning #GraphNeuralNetworks #DeepLearning #UncertaintyQuantification #GeometricDeepLearning
📄 Preprint: arxiv.org/abs/2605.22593
Co-authored w/ @pedrocvieira.bsky.social & Pedro Ribeiro.
#MachineLearning #GraphNeuralNetworks #DeepLearning #UncertaintyQuantification #GeometricDeepLearning
"gRNAde: Geometric Deep Learning for 3D RNA inverse design" by @chaitjo.bsky.social , @arian-jamasb.bsky.social, Ramon Viñas, Charles Harris, Simon Mathis, Alex Morehead, Rishabh Anand, and Pietro Liò
Paper: www.biorxiv.org/content/10.1...
Code: github.com/chaitjo/geom...
#geometricdeeplearning
Paper: www.biorxiv.org/content/10.1...
Code: github.com/chaitjo/geom...
#geometricdeeplearning
November 22, 2024 at 9:47 AM
"gRNAde: Geometric Deep Learning for 3D RNA inverse design" by @chaitjo.bsky.social , @arian-jamasb.bsky.social, Ramon Viñas, Charles Harris, Simon Mathis, Alex Morehead, Rishabh Anand, and Pietro Liò
Paper: www.biorxiv.org/content/10.1...
Code: github.com/chaitjo/geom...
#geometricdeeplearning
Paper: www.biorxiv.org/content/10.1...
Code: github.com/chaitjo/geom...
#geometricdeeplearning
Part 2/2: A huge thank you to our speakers, mentors, participants and sponsors. Looking forward to more exciting talks, projects, and social events over the coming days!
#MachineLearning #GeometricDeepLearning #SummerSchool
#MachineLearning #GeometricDeepLearning #SummerSchool
July 15, 2026 at 2:21 PM
Part 2/2: A huge thank you to our speakers, mentors, participants and sponsors. Looking forward to more exciting talks, projects, and social events over the coming days!
#MachineLearning #GeometricDeepLearning #SummerSchool
#MachineLearning #GeometricDeepLearning #SummerSchool
📣 LOGML'26 Speaker Series
🎤 Soledad Villar @soledadvillar.bsky.social (Johns Hopkins)
Her research spans equivariant ML, GNNs, with applications to computational biology.
📍 Imperial College London
📅 13–17 July 2026
🔗 www.logml.ai
#LOGML #GraphML #GeometricDeepLearning #SummerSchool
🎤 Soledad Villar @soledadvillar.bsky.social (Johns Hopkins)
Her research spans equivariant ML, GNNs, with applications to computational biology.
📍 Imperial College London
📅 13–17 July 2026
🔗 www.logml.ai
#LOGML #GraphML #GeometricDeepLearning #SummerSchool
May 20, 2026 at 4:00 AM
📣 LOGML'26 Speaker Series
🎤 Soledad Villar @soledadvillar.bsky.social (Johns Hopkins)
Her research spans equivariant ML, GNNs, with applications to computational biology.
📍 Imperial College London
📅 13–17 July 2026
🔗 www.logml.ai
#LOGML #GraphML #GeometricDeepLearning #SummerSchool
🎤 Soledad Villar @soledadvillar.bsky.social (Johns Hopkins)
Her research spans equivariant ML, GNNs, with applications to computational biology.
📍 Imperial College London
📅 13–17 July 2026
🔗 www.logml.ai
#LOGML #GraphML #GeometricDeepLearning #SummerSchool
Encoding geometry in neural network architectures has wide applications, from robots' configuration spaces to safety. We present natural ways to enforce constraints by design.
Link to preprint: www.researchgate.net/publication/...
#geometricdeeplearning
Link to preprint: www.researchgate.net/publication/...
#geometricdeeplearning
February 3, 2026 at 2:43 AM
Encoding geometry in neural network architectures has wide applications, from robots' configuration spaces to safety. We present natural ways to enforce constraints by design.
Link to preprint: www.researchgate.net/publication/...
#geometricdeeplearning
Link to preprint: www.researchgate.net/publication/...
#geometricdeeplearning
How can voxels, meshes, and point clouds shape smarter AI in medicine?
Find out at the next #SanoSeminar by Marek Wodziński (Sano & AGH).
💻 Free online: sano.science/seminars/abs...
#AI #MedicalImaging #GeometricDeepLearning
Find out at the next #SanoSeminar by Marek Wodziński (Sano & AGH).
💻 Free online: sano.science/seminars/abs...
#AI #MedicalImaging #GeometricDeepLearning
February 27, 2026 at 10:43 AM
How can voxels, meshes, and point clouds shape smarter AI in medicine?
Find out at the next #SanoSeminar by Marek Wodziński (Sano & AGH).
💻 Free online: sano.science/seminars/abs...
#AI #MedicalImaging #GeometricDeepLearning
Find out at the next #SanoSeminar by Marek Wodziński (Sano & AGH).
💻 Free online: sano.science/seminars/abs...
#AI #MedicalImaging #GeometricDeepLearning
LOGML 2026 mentor applications are still open!
Deadline extended to 22 March 2026(AoE).
Mentor a small team at Imperial College London during 13–17 July'26.
Travel/accommodation support available.
🔗 logml.ai/apply.html
#LOGML #GeometricDeepLearning #GraphML #MachineLearning
Deadline extended to 22 March 2026(AoE).
Mentor a small team at Imperial College London during 13–17 July'26.
Travel/accommodation support available.
🔗 logml.ai/apply.html
#LOGML #GeometricDeepLearning #GraphML #MachineLearning
LOGML 2026
London Geometry and Machine Learning Summer School, July 13-17 2026
logml.ai
March 17, 2026 at 9:39 AM
LOGML 2026 mentor applications are still open!
Deadline extended to 22 March 2026(AoE).
Mentor a small team at Imperial College London during 13–17 July'26.
Travel/accommodation support available.
🔗 logml.ai/apply.html
#LOGML #GeometricDeepLearning #GraphML #MachineLearning
Deadline extended to 22 March 2026(AoE).
Mentor a small team at Imperial College London during 13–17 July'26.
Travel/accommodation support available.
🔗 logml.ai/apply.html
#LOGML #GeometricDeepLearning #GraphML #MachineLearning
Beyond metric preservation: build symplectic structural invariance into representation.
arxiv.org/abs/2512.19409
#ReservoirComputing #RepresentationLearning #InformationGeometry #SymplecticGeometry #HamiltonianDynamics #GeometricDeepLearning #DynamicalSystems #PhysicsInformedML
arxiv.org/abs/2512.19409
#ReservoirComputing #RepresentationLearning #InformationGeometry #SymplecticGeometry #HamiltonianDynamics #GeometricDeepLearning #DynamicalSystems #PhysicsInformedML
Symplectic Reservoir Representation of Legendre Dynamics
Modern learning systems act on internal representations of data, yet how these representations encode underlying physical or statistical structure is often left implicit. In physics, conservation laws...
arxiv.org
December 23, 2025 at 8:54 AM
Beyond metric preservation: build symplectic structural invariance into representation.
arxiv.org/abs/2512.19409
#ReservoirComputing #RepresentationLearning #InformationGeometry #SymplecticGeometry #HamiltonianDynamics #GeometricDeepLearning #DynamicalSystems #PhysicsInformedML
arxiv.org/abs/2512.19409
#ReservoirComputing #RepresentationLearning #InformationGeometry #SymplecticGeometry #HamiltonianDynamics #GeometricDeepLearning #DynamicalSystems #PhysicsInformedML
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion:
We reinterpret learned sheaves as incidence-quiver representations and connect oversmoothing to representation degeneration, stability, and moment-map regularization.
arxiv.org/abs/2605.11178
#GNNs #GeometricDeepLearning
We reinterpret learned sheaves as incidence-quiver representations and connect oversmoothing to representation degeneration, stability, and moment-map regularization.
arxiv.org/abs/2605.11178
#GNNs #GeometricDeepLearning
May 18, 2026 at 8:04 PM
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion:
We reinterpret learned sheaves as incidence-quiver representations and connect oversmoothing to representation degeneration, stability, and moment-map regularization.
arxiv.org/abs/2605.11178
#GNNs #GeometricDeepLearning
We reinterpret learned sheaves as incidence-quiver representations and connect oversmoothing to representation degeneration, stability, and moment-map regularization.
arxiv.org/abs/2605.11178
#GNNs #GeometricDeepLearning
Some of the best moments in 3D computer vision are when a geometric proof explains why an algorithm works—or why it fails. There’s something satisfying about seeing clean math in noisy point clouds 🤔 #GeometricDeepLearning #ItzikThoughtLoop
October 24, 2025 at 4:08 PM
Some of the best moments in 3D computer vision are when a geometric proof explains why an algorithm works—or why it fails. There’s something satisfying about seeing clean math in noisy point clouds 🤔 #GeometricDeepLearning #ItzikThoughtLoop
🤓 We match or achieve SotA results among TDL models with orders of magnitude less complexity!
🫂 Amazing joint work with @GDasoulas, @mauriciogtec, @ekarais43, @audiracmichelle, @francescadomin8
#TopologicalDeepLearning #GeometricDeepLearning #EquivariantNeuralNetworks
🫂 Amazing joint work with @GDasoulas, @mauriciogtec, @ekarais43, @audiracmichelle, @francescadomin8
#TopologicalDeepLearning #GeometricDeepLearning #EquivariantNeuralNetworks
January 22, 2025 at 7:14 PM
🤓 We match or achieve SotA results among TDL models with orders of magnitude less complexity!
🫂 Amazing joint work with @GDasoulas, @mauriciogtec, @ekarais43, @audiracmichelle, @francescadomin8
#TopologicalDeepLearning #GeometricDeepLearning #EquivariantNeuralNetworks
🫂 Amazing joint work with @GDasoulas, @mauriciogtec, @ekarais43, @audiracmichelle, @francescadomin8
#TopologicalDeepLearning #GeometricDeepLearning #EquivariantNeuralNetworks
Very nice presentation by @omendezlucio about their recently published piece using #geometricdeeplearning to predict protein-ligand binding interactions #drugdiscovery #artificialintelligence
nature.com/articles/s4225…
nature.com/articles/s4225…
A geometric deep learning approach to predict binding conformations of bioactive molecules
Nature Machine Intelligence - Predicting binding of ligands to molecular targets is a key task in the development of new drugs. To improve the speed and accuracy of this prediction,...
www.nature.com
December 13, 2024 at 10:55 AM
Very nice presentation by @omendezlucio about their recently published piece using #geometricdeeplearning to predict protein-ligand binding interactions #drugdiscovery #artificialintelligence
nature.com/articles/s4225…
nature.com/articles/s4225…
📏We adapt existing graph neural networks and transformers to take neural graphs as input, and incorporate inductive biases from neural graphs.
In the context of #geometricdeeplearning, neural graphs constitute a new benchmark for graph neural networks.
[7/9]
In the context of #geometricdeeplearning, neural graphs constitute a new benchmark for graph neural networks.
[7/9]
February 7, 2025 at 10:20 AM
📏We adapt existing graph neural networks and transformers to take neural graphs as input, and incorporate inductive biases from neural graphs.
In the context of #geometricdeeplearning, neural graphs constitute a new benchmark for graph neural networks.
[7/9]
In the context of #geometricdeeplearning, neural graphs constitute a new benchmark for graph neural networks.
[7/9]