Preface to GRaM: the Second Workshop on Geometry-grounded Representation Learning and Generative Modeling

Alison Pouplin, Sharvaree Vadgama, Erik Bekkers, Sékou-Oumar Kaba, Hannah Lawrence, Manuel Lecha, Elizabeth Baker, Julian Suk, Robin Walters, Jakub Tomczak, Stefanie Jegelka
Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, PMLR 326:1-4, 2026.

Abstract

This second edition of GRaM, the workshop on Geometry-grounded Representation Learning and Generative Modeling, was held at ICLR 2026 in Rio de Janeiro. GRaM is built on the principle of grounding in geometry — that machine learning models should respect the geometric structure of their data, from symmetries and manifolds to graphs and non-Euclidean spaces, rather than treat their inputs as plain vectors. This year we asked whether such structure holds up under the theme scale and simplicity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v326-pouplin26a, title = {Preface to GRaM: the Second Workshop on Geometry-grounded Representation Learning and Generative Modeling}, author = {Pouplin, Alison and Vadgama, Sharvaree and Bekkers, Erik and Kaba, S\'ekou-Oumar and Lawrence, Hannah and Lecha, Manuel and Baker, Elizabeth and Suk, Julian and Walters, Robin and Tomczak, Jakub and Jegelka, Stefanie}, booktitle = {Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling}, pages = {1--4}, year = {2026}, editor = {Pouplin, Alison and Vadgama, Sharvaree and Bekkers, Erik and Kaba, Sékou-Oumar and Lawrence, Hannah and Lecha, Manuel and Baker, Elizabeth and Suk, Julian and Walters, Robin and Tomczak, Jakub and Jegelka, Stefanie}, volume = {326}, series = {Proceedings of Machine Learning Research}, month = {26 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v326/main/assets/pouplin26a/pouplin26a.pdf}, url = {https://proceedings.mlr.press/v326/pouplin26a.html}, abstract = {This second edition of GRaM, the workshop on Geometry-grounded Representation Learning and Generative Modeling, was held at ICLR 2026 in Rio de Janeiro. GRaM is built on the principle of grounding in geometry — that machine learning models should respect the geometric structure of their data, from symmetries and manifolds to graphs and non-Euclidean spaces, rather than treat their inputs as plain vectors. This year we asked whether such structure holds up under the theme scale and simplicity.} }
Endnote
%0 Conference Paper %T Preface to GRaM: the Second Workshop on Geometry-grounded Representation Learning and Generative Modeling %A Alison Pouplin %A Sharvaree Vadgama %A Erik Bekkers %A Sékou-Oumar Kaba %A Hannah Lawrence %A Manuel Lecha %A Elizabeth Baker %A Julian Suk %A Robin Walters %A Jakub Tomczak %A Stefanie Jegelka %B Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling %C Proceedings of Machine Learning Research %D 2026 %E Alison Pouplin %E Sharvaree Vadgama %E Erik Bekkers %E Sékou-Oumar Kaba %E Hannah Lawrence %E Manuel Lecha %E Elizabeth Baker %E Julian Suk %E Robin Walters %E Jakub Tomczak %E Stefanie Jegelka %F pmlr-v326-pouplin26a %I PMLR %P 1--4 %U https://proceedings.mlr.press/v326/pouplin26a.html %V 326 %X This second edition of GRaM, the workshop on Geometry-grounded Representation Learning and Generative Modeling, was held at ICLR 2026 in Rio de Janeiro. GRaM is built on the principle of grounding in geometry — that machine learning models should respect the geometric structure of their data, from symmetries and manifolds to graphs and non-Euclidean spaces, rather than treat their inputs as plain vectors. This year we asked whether such structure holds up under the theme scale and simplicity.
APA
Pouplin, A., Vadgama, S., Bekkers, E., Kaba, S., Lawrence, H., Lecha, M., Baker, E., Suk, J., Walters, R., Tomczak, J. & Jegelka, S.. (2026). Preface to GRaM: the Second Workshop on Geometry-grounded Representation Learning and Generative Modeling. Proceedings of GRaM: the Second Edition of the Workshop on Geometry-grounded Representation Learning and Generative Modeling, in Proceedings of Machine Learning Research 326:1-4 Available from https://proceedings.mlr.press/v326/pouplin26a.html.

Related Material