Erik Bekkers
@erikjbekkers.bsky.social
AMLab, Informatics Institute, University of Amsterdam. ELLIS Scholar. Geometry-Grounded Representation Learning. Equivariant Deep Learning.
Reposted by Erik Bekkers
There's an increasingly popular argument saying that for 3D point clouds with rotational ambiguity (e.g. molecular data) standard transformers are preferable over equivariant models for compute reasons. With “Platonic Transformers” we show why this doesn't have to be true. arxiv.org/abs/2510.03511
Platonic Transformers: A Solid Choice For Equivariance
While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that ma...
arxiv.org
October 23, 2025 at 2:35 PM
There's an increasingly popular argument saying that for 3D point clouds with rotational ambiguity (e.g. molecular data) standard transformers are preferable over equivariant models for compute reasons. With “Platonic Transformers” we show why this doesn't have to be true. arxiv.org/abs/2510.03511
Reposted by Erik Bekkers
Enschede crowd you don't want to miss this! Join us for two exciting talks by Jolanda Wentzel and @erikjbekkers.bsky.social. As a bonus, you get to see me in "appropriate traditional dress from [my] country of origin".
📅 28 May
📍 UTwente campus
📅 28 May
📍 UTwente campus
May 24, 2025 at 12:23 PM
Enschede crowd you don't want to miss this! Join us for two exciting talks by Jolanda Wentzel and @erikjbekkers.bsky.social. As a bonus, you get to see me in "appropriate traditional dress from [my] country of origin".
📅 28 May
📍 UTwente campus
📅 28 May
📍 UTwente campus
Reposted by Erik Bekkers
New PhD position at the University of Amsterdam in @amlab.bsky.social on learning concepts with theoretical guarantees using #causality and #RL with me, Frans Oliehoek (TU Delft) and Herke van Hoof 💥
Deadline: 15 June
werkenbij.uva.nl/en/vacancies...
Deadline: 15 June
werkenbij.uva.nl/en/vacancies...
Vacancy — PhD Position on Learning Concepts with Theoretical Guarantees Using Causality and RL
Are you interested in improving the interpretability, robustness and safety of current AI systems? If the answer is yes, please continue reading!
werkenbij.uva.nl
May 12, 2025 at 5:03 PM
New PhD position at the University of Amsterdam in @amlab.bsky.social on learning concepts with theoretical guarantees using #causality and #RL with me, Frans Oliehoek (TU Delft) and Herke van Hoof 💥
Deadline: 15 June
werkenbij.uva.nl/en/vacancies...
Deadline: 15 June
werkenbij.uva.nl/en/vacancies...
Reposted by Erik Bekkers
💬 Join TODAY’s webinar: “Symmetry, scale, and science: A geometric path to better AI" by @erikjbekkers.bsky.social & @jobrandstetter.bsky.social
(ELLIS Program “Geometric Deep Learning”)
🗓️ Mon, March 10, 2025
🕓 16:00-17:00 CET
🔗 Register here: aiforgood.itu.int/event/symmet...
(ELLIS Program “Geometric Deep Learning”)
🗓️ Mon, March 10, 2025
🕓 16:00-17:00 CET
🔗 Register here: aiforgood.itu.int/event/symmet...
Symmetry, scale, and science: A geometric path to better AI
The success of modern AI systems has been largely driven by massive scaling of data and compute resources. However, in scientific applications, where
aiforgood.itu.int
March 10, 2025 at 12:17 PM
💬 Join TODAY’s webinar: “Symmetry, scale, and science: A geometric path to better AI" by @erikjbekkers.bsky.social & @jobrandstetter.bsky.social
(ELLIS Program “Geometric Deep Learning”)
🗓️ Mon, March 10, 2025
🕓 16:00-17:00 CET
🔗 Register here: aiforgood.itu.int/event/symmet...
(ELLIS Program “Geometric Deep Learning”)
🗓️ Mon, March 10, 2025
🕓 16:00-17:00 CET
🔗 Register here: aiforgood.itu.int/event/symmet...
Reposted by Erik Bekkers
Super happy to share our work was accepted as an Oral at the Delta Workshop @ ICLR 2025! 🎉
Can’t wait to talk about it in Singapore 😎
Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social 🔥
Can’t wait to talk about it in Singapore 😎
Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social 🔥
Variational Flow Matching goes Riemannian! 🔮
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
March 6, 2025 at 2:03 PM
Super happy to share our work was accepted as an Oral at the Delta Workshop @ ICLR 2025! 🎉
Can’t wait to talk about it in Singapore 😎
Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social 🔥
Can’t wait to talk about it in Singapore 😎
Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social 🔥
🚀 Excited to be part of this project led by Praneeta Konduri! We’re using state-of-the-art generative models to create synthetic vasculature geometries—pushing stroke treatment development forward while cutting down on patient data reliance. Exciting stuff! 😃 rdt.uva.nl/research/res...
Synthetic data to enhance new treatment uptake for acute ischemic stroke - Responsible Digital Transformations
Multiple (pre-)clinical trials are required in the regulatory trajectory to introduce new medical devices in clinical practice. The process is widely acknowledged as sub-optimal, resource-heavy, and t...
rdt.uva.nl
February 26, 2025 at 7:27 AM
🚀 Excited to be part of this project led by Praneeta Konduri! We’re using state-of-the-art generative models to create synthetic vasculature geometries—pushing stroke treatment development forward while cutting down on patient data reliance. Exciting stuff! 😃 rdt.uva.nl/research/res...
Reposted by Erik Bekkers
Variational Flow Matching goes Riemannian! 🔮
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
February 19, 2025 at 3:13 PM
Variational Flow Matching goes Riemannian! 🔮
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.
Dream team: Floor, Alison & Erik (their @ below) 💥
📜 arxiv.org/abs/2502.12981
🧵1/5
Reposted by Erik Bekkers
Common beliefs about equivariant networks for image input include 1) They are slow. 2) They don’t scale to ImageNet. 3) They are complicated. In my opinion, these three are all false. To argue against them, we made minimal modifications to popular vision models, turning them mirror-equivariant.
February 10, 2025 at 7:35 AM
Common beliefs about equivariant networks for image input include 1) They are slow. 2) They don’t scale to ImageNet. 3) They are complicated. In my opinion, these three are all false. To argue against them, we made minimal modifications to popular vision models, turning them mirror-equivariant.
Reposted by Erik Bekkers
Really excited about this! We note a connection between diffusion/flow models and neural/latent SDEs. We show how to use this for simulation-free learning of fully flexible SDEs. We refer to this as SDE Matching and show speed improvements of several orders of magnitude.
arxiv.org/abs/2502.02472
arxiv.org/abs/2502.02472
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend ...
arxiv.org
February 5, 2025 at 2:38 PM
Really excited about this! We note a connection between diffusion/flow models and neural/latent SDEs. We show how to use this for simulation-free learning of fully flexible SDEs. We refer to this as SDE Matching and show speed improvements of several orders of magnitude.
arxiv.org/abs/2502.02472
arxiv.org/abs/2502.02472
Reposted by Erik Bekkers
✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social
👇👇👇 @ellisamsterdam.bsky.social
February 3, 2025 at 7:44 AM
✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social
👇👇👇 @ellisamsterdam.bsky.social
Reposted by Erik Bekkers
Accepted to ICLR 🚨 Does using more geometry always help with molecule property prediction? In practice, we deal with imperfect geometries, which introduce structural noise.
In our work arxiv.org/abs/2410.11933, we investigate when and how geometric information is useful (or not) for RNA molecules.
In our work arxiv.org/abs/2410.11933, we investigate when and how geometric information is useful (or not) for RNA molecules.
Beyond Sequence: Impact of Geometric Context for RNA Property Prediction
Accurate prediction of RNA properties, such as stability and interactions, is crucial for advancing our understanding of biological processes and developing RNA-based therapeutics. RNA structures can ...
arxiv.org
February 3, 2025 at 8:55 AM
Accepted to ICLR 🚨 Does using more geometry always help with molecule property prediction? In practice, we deal with imperfect geometries, which introduce structural noise.
In our work arxiv.org/abs/2410.11933, we investigate when and how geometric information is useful (or not) for RNA molecules.
In our work arxiv.org/abs/2410.11933, we investigate when and how geometric information is useful (or not) for RNA molecules.
Reposted by Erik Bekkers
🔥 3/4 #ICLR2025 Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ENF), for geometry-informed continuous signal representations openreview.net/forum?id=A4e...
+@dafidofff.bsky.social, @davidmknigge.bsky.social @erikjbekkers.bsky.social S. Papa, R. Valperga, S. Vadgama
+@dafidofff.bsky.social, @davidmknigge.bsky.social @erikjbekkers.bsky.social S. Papa, R. Valperga, S. Vadgama
Grounding Continuous Representations in Geometry: Equivariant...
Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone...
openreview.net
January 23, 2025 at 2:00 PM
🔥 3/4 #ICLR2025 Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ENF), for geometry-informed continuous signal representations openreview.net/forum?id=A4e...
+@dafidofff.bsky.social, @davidmknigge.bsky.social @erikjbekkers.bsky.social S. Papa, R. Valperga, S. Vadgama
+@dafidofff.bsky.social, @davidmknigge.bsky.social @erikjbekkers.bsky.social S. Papa, R. Valperga, S. Vadgama
Reposted by Erik Bekkers
🚀 AI for Good Webinar Launch: From Molecules to Models
Next week, ELLIS kicks off a new webinar series on AI in life sciences, showcasing key research from ELLIS Programs.
🗓️ Date: Feb 3, 2025
🕓 Time: 16:00-17:30 CET
Register: aiforgood.itu.int/event/unlear...
Next week, ELLIS kicks off a new webinar series on AI in life sciences, showcasing key research from ELLIS Programs.
🗓️ Date: Feb 3, 2025
🕓 Time: 16:00-17:30 CET
Register: aiforgood.itu.int/event/unlear...
Unlearning Toxicity in Multimodal Foundation Models & Learning to design protein-protein interactions with enhanced generalization
Part 1 (Rita Cucchiara): Foundation Models, pretrained on extremely large unknown source of data, contain in their embed space many information
aiforgood.itu.int
January 29, 2025 at 1:58 PM
🚀 AI for Good Webinar Launch: From Molecules to Models
Next week, ELLIS kicks off a new webinar series on AI in life sciences, showcasing key research from ELLIS Programs.
🗓️ Date: Feb 3, 2025
🕓 Time: 16:00-17:30 CET
Register: aiforgood.itu.int/event/unlear...
Next week, ELLIS kicks off a new webinar series on AI in life sciences, showcasing key research from ELLIS Programs.
🗓️ Date: Feb 3, 2025
🕓 Time: 16:00-17:30 CET
Register: aiforgood.itu.int/event/unlear...
Reposted by Erik Bekkers
♻️Learning Symmetries via Weight-sharing with Doubly Stochastic Tensors
by Putri van der Linden, @algarciacast.bsky.social, @sharvaree.bsky.social, Thijs P. Kuipers, @erikjbekkers.bsky.social
🪪https://neurips.cc/virtual/2024/poster/96699
📜https://arxiv.org/abs/2412.04594
🧵9/ 12
by Putri van der Linden, @algarciacast.bsky.social, @sharvaree.bsky.social, Thijs P. Kuipers, @erikjbekkers.bsky.social
🪪https://neurips.cc/virtual/2024/poster/96699
📜https://arxiv.org/abs/2412.04594
🧵9/ 12
Learning Symmetries via Weight-Sharing with Doubly Stochastic Tensors
Group equivariance has emerged as a valuable inductive bias in deep learning, enhancing generalization, data efficiency, and robustness. Classically, group equivariant methods require the groups of in...
arxiv.org
December 9, 2024 at 1:24 PM
♻️Learning Symmetries via Weight-sharing with Doubly Stochastic Tensors
by Putri van der Linden, @algarciacast.bsky.social, @sharvaree.bsky.social, Thijs P. Kuipers, @erikjbekkers.bsky.social
🪪https://neurips.cc/virtual/2024/poster/96699
📜https://arxiv.org/abs/2412.04594
🧵9/ 12
by Putri van der Linden, @algarciacast.bsky.social, @sharvaree.bsky.social, Thijs P. Kuipers, @erikjbekkers.bsky.social
🪪https://neurips.cc/virtual/2024/poster/96699
📜https://arxiv.org/abs/2412.04594
🧵9/ 12
Reposted by Erik Bekkers
🐑 Come and check out Variational Flow Matching for Graph Generation next week at @neuripsconf.bsky.social ! 🐑
Wed 11 Dec 11 a.m. PST — 2 p.m. PST
West Ballroom A-D #7103
arxiv.org/abs/2406.04843
Wed 11 Dec 11 a.m. PST — 2 p.m. PST
West Ballroom A-D #7103
arxiv.org/abs/2406.04843
December 6, 2024 at 10:20 PM
🐑 Come and check out Variational Flow Matching for Graph Generation next week at @neuripsconf.bsky.social ! 🐑
Wed 11 Dec 11 a.m. PST — 2 p.m. PST
West Ballroom A-D #7103
arxiv.org/abs/2406.04843
Wed 11 Dec 11 a.m. PST — 2 p.m. PST
West Ballroom A-D #7103
arxiv.org/abs/2406.04843
Reposted by Erik Bekkers
Meet our Lab's members: staff, postdocs and PhD students! :)
With this starter pack you can easily connect with us and keep up to date with all the member's research and news 🦋
go.bsky.app/8EGigUy
With this starter pack you can easily connect with us and keep up to date with all the member's research and news 🦋
go.bsky.app/8EGigUy
November 21, 2024 at 9:22 PM
Meet our Lab's members: staff, postdocs and PhD students! :)
With this starter pack you can easily connect with us and keep up to date with all the member's research and news 🦋
go.bsky.app/8EGigUy
With this starter pack you can easily connect with us and keep up to date with all the member's research and news 🦋
go.bsky.app/8EGigUy
Reposted by Erik Bekkers
A starter pack for researchers interested in Geometric Deep Learning - in the broadest sense possible!
Let me know if you would like to be listed. :)
Thanks @sharvaree.bsky.social for the idea!
go.bsky.app/7h8sek
Let me know if you would like to be listed. :)
Thanks @sharvaree.bsky.social for the idea!
go.bsky.app/7h8sek
November 20, 2024 at 3:35 PM
A starter pack for researchers interested in Geometric Deep Learning - in the broadest sense possible!
Let me know if you would like to be listed. :)
Thanks @sharvaree.bsky.social for the idea!
go.bsky.app/7h8sek
Let me know if you would like to be listed. :)
Thanks @sharvaree.bsky.social for the idea!
go.bsky.app/7h8sek
Reposted by Erik Bekkers
Soon, @erikjbekkers.bsky.social and @davidmknigge.bsky.social will give a talk elaborating even further on geometry-grounded representation learning in a NeurReps seminar. Make sure to mark the date! :)
⏰ November 21st, 4 PM CET
🔗 www.neurreps.org/speaker-seri...
⏰ November 21st, 4 PM CET
🔗 www.neurreps.org/speaker-seri...
November 19, 2024 at 4:14 PM
Soon, @erikjbekkers.bsky.social and @davidmknigge.bsky.social will give a talk elaborating even further on geometry-grounded representation learning in a NeurReps seminar. Make sure to mark the date! :)
⏰ November 21st, 4 PM CET
🔗 www.neurreps.org/speaker-seri...
⏰ November 21st, 4 PM CET
🔗 www.neurreps.org/speaker-seri...