The GRaM (Geometry-grounded Representation Learning and Generative Modeling) workshop at
#ICML2024
is kicking off now with opening remarks!
Ready to explore groundbreaking with our amazing speakers, panelists and poster presenters! 🌟
We are now thrilled to have a talk by
@ZKadkhodaie
presenting "Generalization in diffusion models arises from geometry-adaptive harmonic representations"🌐
Equivariance is all about the preservation of known symmetries. But if we don't know the symmetries of our system, can we discover it directly from data? For the final talk of the
#GRaM
workshop,
@yuqirose
shows us how 🧊🛞
🌟 Announcements of the TAG ML Challenge winners with
@gbg1441
and
@lev_telyatnikov
! Participants dove into the world of Topological Deep Learning and created mappings between different topological domains.
More information here:
That concludes our talk series at
#GRaM
! Before heading out from the conference center, don't miss the second poster session -- featuring all new posters -- from 4:05pm to 4:55pm.
🧵 Our geometric
@GRaM_org_
workshop has released the accepted blog posts and tutorials! Theory can be hard to digest, and educational materials are scarce. We are impressed by the students' work!
Some of my favorites ⬇️
We are now delighted to have Yoav Gelberg presenting "Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks" 📊
@GRaM_org_
@yuqirose
@phillip_isola
@ninamiolane
@bose_joey
3. Meng Song will share her work 'Probabilistic World Modeling with Asymmetric Distance Measure'
4. Amine will talk on 'Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space'
5. Jacob will give a talk on 'Bundle Neural Networks for message diffusion on
🏆 The time has finally come! 🏆
Announcing the winners of the 2nd edition of the Topological Deep Learning Challenge at
#ICML2024
, hosted at
@GRaM_workshop
!
Next up, we have
@ninamiolane
as our invited speaker talking about everything beyond Euclidean geometry.
I would like to specially thanks to Nina for presenting from Santa Barbara, local time 5:50 am on a Saturday 🥺🥰
@GRaM_org_
@yuqirose
@phillip_isola
@ninamiolane
@bose_joey
We have an amazing list of contributed talks (orals) at
@GRaM_org_
1. Berfin will give a talk on 'Adaptive Sampling for Continuous Group Equivariant Neural Networks'
2. Yoav will talk about 'Variational Inference Failures Under Model Symmetries: Permutation Invariant
Thank you all for making this TAG-ML
@icml
gathering a huge success! It was a wonderful turnout— we enjoyed getting to meet you. We look forward to seeing many of you at the
@GRaM_org_
workshop on Saturday and hope to see you at another TAG event very soon ❤️
@SharvVadgama
@GRaM_org_
@GRaM_workshop
@icmlconf
Follow
@GRaM_org_
: Geometry-Grounded Representation Learning and Generative Modeling! We've got an amazing workshop coming up (Sat 27 July,
@icmlconf
), w many inspiring talks (), and a beautiful set of contributions to appear in our proceedings! Stay tuned!