GRaM Workshop at ICML 2024

🎉Happy to be in 🇨🇦Vancouver in the summer for ✨ICML2025! Ping me if you want to chat about Symmetries, GDL, Geometric representations + AI4Science, or want to look for the best ramen in town🍜! 🥁Excited to present a few exciting works at the main conference and workshops!…

I deeply appreciate @chaitjo's work & keeping this discussion going! Valuable to keep us sharp+avoid dogma. Tho, I'm a lost soul, 'equivariance extremist'😅. Admittingly, I do opt for simplicity over equivariance at times🙈, but my vision: they aren't mutually exclusive! 5/5

3. 💪 Rapidash: Scalable Molecular Modeling Through Controlled Equivariance Breaking Presenting 💪🚀Rapidash🚀 architecture: a flexible architecture allowing for different symmetry-breaking, equivariance-breaking modes through a group convolutional architecture at…

Here horizontal axis is train time: on an exactly equal computate budget, equiv models greatly outperform non-equiv ones. Scale all you want 😉(we tried!), the performance gap just could not be closed🤷‍♂️. Even on non-equivariant tasks equivariant models performed favorably. 2/5

Great discussion, @chaitjo! We also explored this with extensive experiments in our recent paper: arxiv.org/abs/2501.01999. We find, among others, that equiv mods in a sense scale even better than non-equiv ones. Going more or less completely against the vibes from your post😅1/5

@GRaM_org_ featured in @Ellis_Amsterdam !

Thank you @Ellis_Amsterdam for featuring #GRaM workshop that happened earlier this year at #ICML2024 in Vienna. I had a lot of fun organizing this workshop alongside my wonderful advisors @erikjbekkers @jmtomczak and with an incredible team. This wouldn't have been possible…

The workshop was successfully organised by @SharvVadgama @erikjbekkers @jmtomczak Alison Pouplin, Robin Walters, Hannah Lawrence, Sékou-Oumar Kaba, Tegan Emerson, Henry Kvinge , and Stefanie Jegelka

🚀Introducing — Meta Flow Matching (MFM) 🚀 Imagine predicting patient-specific treatment responses for unseen cases or building generative models that adapt across different measures. MFM makes this a reality. 📰Paper: arxiv.org/abs/2408.14608 💻Code: github.com/lazaratan/meta…

Very relevant workshop for ✨ @GRaM_org_ audience! ✨

I am very excited about the 🌟NeurReps Global Talk series 🌟—another great initiative by NeurReps Team🥳 East Coast folks, do join in-person!

Had a great time participating in the @GRaM_org_ challenge at #ICML2024! It was an incredible experience implementing different liftings and passing constructions from pure math. Many thanks to the organizers @PyT_Team_ @gbg1441 @lev_telyatnikov!

Very happy that our work received the Best Paper Runner-up Award at the @GRaM_org_! Huge thanks to the organizers, especially @SharvVadgama, for organizing this amazing workshop. And congrats to all my co-authors @n_gao96, @j_m_sommer, @TomWollschlager, @guennemann. #ICML2024

I'm also excited to share that our work has been accepted for an oral presentation. Huge thanks to the @GRaM_org_ organizers for this recognition and the opportunity to present our work! (4/4)

I am happy to introduce our work "Adaptive Sampling for Continuous Group Equivariant Neural Networks" with @_gabrielecesa_ : openreview.net/forum?id=fZNgs… Excited to have received the Best Paper Runner-up award at the @GRaM_org_ !  #ICML2024 Here is a brief summary (1/4)

Very proud of my student @sberfininal. Her thesis received the best paper runner-up award at the @GRaM_org_ at #ICML24 Check the paper if you are interested in continuous equivariance and steerable networks

Many thanks to the @GRaM_org_ organizers for making it possible as well as @erikjbekkers for this amazing #UniversityofAmsterdam representation! 👏

Thrilled to receive the outstanding paper award together with @Mangal_Prakash_ for our work on SE(3)-Hyena arxiv.org/abs/2407.01049 !🤘 Go long-convolutions!

Thrilled and honored to receive the Outstanding Paper Award @GRaM_org_ #ICML2024 for our SE(3)-Hyena paper arxiv.org/abs/2407.01049. Huge thanks to my co-author @artemmoskalev and everyone who supported our work. Excited to see where this research leads next! #OutstandingPaper

Thank you @SharvVadgama and the @GRaM_org_ team for an incredible workshop!