Skip to yearly menu bar Skip to main content


Workshop

Symmetry and Geometry in Neural Representations

Sophia Sanborn ⋅ Christian A Shewmake ⋅ Simone Azeglio ⋅ Nina Miolane
Project Page

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
8:00 AM
Coffee Break
10:00 AM
Lunch Break
12:30 PM
Physics Priors in Machine Learning
Max Welling
1:00 PM
Coffee Break
2:05 PM
Poster Session
Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks
Sho Sonoda ⋅ Hideyuki Ishi ⋅ Isao Ishikawa ⋅ Masahiro Ikeda
Towards Information Theory-Based Discovery of Equivariances
Hippolyte Charvin ⋅ Nicola Catenacci Volpi ⋅ Daniel Polani
Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activity
Christopher Versteeg ⋅ Andrew Sedler ⋅ Jonathan McCart ⋅ Chethan Pandarinath
Data Augmentations in Deep Weight Spaces
Aviv Shamsian ⋅ David Zhang ⋅ Aviv Navon ⋅ Yan Zhang ⋅ Miltiadis (Miltos) Kofinas ⋅ Idan Achituve ⋅ Riccardo Valperga ⋅ Gertjan Burghouts ⋅ Efstratios Gavves ⋅ Cees Snoek ⋅ Ethan Fetaya ⋅ Gal Chechik ⋅ Haggai Maron
Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds
Henry Kvinge ⋅ Grayson Jorgenson ⋅ Davis Brown ⋅ Charles Godfrey ⋅ Tegan Emerson
Spectral Maps for Learning on Subgraphs
Marco Pegoraro ⋅ Riccardo Marin ⋅ Arianna Rampini ⋅ Simone Melzi ⋅ Luca Cosmo ⋅ Emanuele Rodolà
On Complex Network Dynamics of an In-Vitro Neuronal System during Rest and Gameplay
Moein Khajehnejad ⋅ Forough Habibollahi ⋅ Alon Loeffler ⋅ Brett J. Kagan ⋅ Adeel Razi
Symmetry Breaking and Equivariant Neural Networks
Oumar Kaba ⋅ Siamak Ravanbakhsh
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
Irene Cannistraci ⋅ Luca Moschella ⋅ Marco Fumero ⋅ Valentino Maiorca ⋅ Emanuele Rodolà
Learning Useful Representations of Recurrent Neural Network Weight Matrices
Vincent Herrmann ⋅ Francesco Faccio ⋅ Jürgen Schmidhuber
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations
Victor Lecomte ⋅ Rylan Schaeffer ⋅ Berivan Isik ⋅ Mikail Khona ⋅ Yann LeCun ⋅ Sanmi Koyejo ⋅ Andrey Gromov ⋅ Ravid Shwartz-Ziv
AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inference
Yuan Lu ⋅ Haitz Sáez de Ocáriz Borde ⋅ Pietro Lió
How do language models bind entities in context?
Jiahai Feng ⋅ Jacob Steinhardt
Improving Convergence and Generalization Using Parameter Symmetries
Bo Zhao ⋅ Robert Gower ⋅ Robin Walters ⋅ Rose Yu
Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus
Cody Tipton ⋅ Elizabeth Coda ⋅ Davis Brown ⋅ Alyson Bittner ⋅ Caitlin Hutten ⋅ Grayson Jorgenson ⋅ Tegan Emerson ⋅ Henry Kvinge
How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks
Rahul Ramesh ⋅ Mikail Khona ⋅ Robert Dick ⋅ Hidenori Tanaka ⋅ Ekdeep S Lubana
Structure-wise Uncertainty for Curvilinear Image Segmentation
Saumya Gupta ⋅ Xiaoling Hu ⋅ Chao Chen
On the Varied Faces of Overparameterization in Supervised and Self-Supervised Learning
Matteo Gamba ⋅ Arna Ghosh ⋅ Kumar Krishna Agrawal ⋅ Blake Richards ⋅ Hossein Azizpour ⋅ Mårten Björkman
Geometric Epitope and Paratope Prediction
Marco Pegoraro ⋅ Clémentine Dominé ⋅ Emanuele Rodolà ⋅ Petar Veličković ⋅ Andreea-Ioana Deac
RelWire: Metric Based Graph Rewiring
Rishi Sonthalia ⋅ Anna Gilbert ⋅ Matthew Durham
Sheaf-based Positional Encodings for Graph Neural Networks
Yu He ⋅ Cristian Bodnar ⋅ Pietro Lió
Structural Similarities Between Language Models and Neural Response Measurements
Jiaang Li ⋅ Antonia Karamolegkou ⋅ Yova Kementchedjhieva ⋅ Mostafa Abdou ⋅ Sune Lehmann ⋅ Anders Søgaard
INRFormer: Neuron Permutation Equivariant Transformer on Implicit Neural Representations
Lei Zhou ⋅ Varun Belagali ⋅ Joseph Bae ⋅ Prateek Prasanna ⋅ Dimitris Samaras
From Charts to Atlas: Merging Latent Spaces into One
Donato Crisostomi ⋅ Irene Cannistraci ⋅ Luca Moschella ⋅ Pietro Barbiero ⋅ Marco Ciccone ⋅ Pietro Lió ⋅ Emanuele Rodolà
Growing Brains in Recurrent Neural Networks for Multiple Cognitive Tasks
Ziming Liu ⋅ Mikail Khona ⋅ Ila Fiete ⋅ Max Tegmark
Are “Hierarchical” Visual Representations Hierarchical?
Ethan Shen ⋅ Ali Farhadi ⋅ Aditya Kusupati
Homological Convolutional Neural Networks
Antonio Briola ⋅ Yuanrong Wang ⋅ Silvia Bartolucci ⋅ Tomaso Aste
Visual Scene Representation with Hierarchical Equivariant Sparse Coding
Christian A Shewmake ⋅ Domas Buracas ⋅ Hansen Lillemark ⋅ Jinho Shin ⋅ Erik Bekkers ⋅ Nina Miolane ⋅ Bruno Olshausen
Symmetry-based Learning of Radiance Fields for Rigid Objects
Zhiwei Han ⋅ Stefan Matthes ⋅ Hao Shen ⋅ Yuanting Liu
Decorrelating neurons using persistence
Rubén Ballester ⋅ Carles Casacuberta ⋅ Sergio Escalera
Scalar Invariant Networks with Zero Bias
Chuqin Geng ⋅ Xiaojie Xu ⋅ Haolin Ye ⋅ Xujie Si
Fast Temporal Wavelet Graph Neural Networks
Duc Thien Nguyen ⋅ Tuan Nguyen ⋅ Truong Son Hy ⋅ Risi Kondor
Pitfalls in Measuring Neural Transferability
Suryaka Suresh ⋅ Vinayak Abrol ⋅ Anshul Thakur
Random Field Augmentations for Self-Supervised Representation Learning
Philip Mansfield ⋅ Arash Afkanpour ⋅ Warren Morningstar ⋅ Karan Singhal
Roto-translation Equivariant YOLO for Aerial Images
Benjamin Maurel ⋅ Samy Blusseau ⋅ Santiago Velasco-Forero ⋅ Teodora Petrisor
Testing Assumptions Underlying a Unified Theory for the Origin of Grid Cells
Rylan Schaeffer ⋅ Mikail Khona ⋅ Adrian Bertagnoli ⋅ Sanmi Koyejo ⋅ Ila Fiete
SO(3)-Equivariant Representation Learning in 2D Images
Darnell Granberry ⋅ Alireza Nasiri ⋅ Jiayi Shou ⋅ Alex J. Noble ⋅ Tristan Bepler
On the Information Geometry of Vision Transformers
Sonia Joseph ⋅ Kumar Krishna Agrawal ⋅ Arna Ghosh ⋅ Blake Richards
The Variability of Representations in Mice and Humans Changes with Learning, Engagement, and Attention
Praveen Venkatesh ⋅ Corbett Bennett ⋅ Sam Gale ⋅ Juri Minxha ⋅ Hristos Courellis ⋅ Greggory Heller ⋅ Tamina Ramirez ⋅ Severine Durand ⋅ Ueli Rutishauser ⋅ Shawn Olsen ⋅ Stefan Mihalas
Explicit Neural Surfaces: Learning Continuous Geometry with Deformation Fields
Thomas Walker ⋅ Octave Mariotti ⋅ Amir Vaxman ⋅ Hakan Bilen
Symmetric Models for Radar Response Modeling
Colin Kohler ⋅ Nathan Vaska ⋅ Ramya Muthukrishnan ⋅ Whangbong Choi ⋅ Jung Yeon Park ⋅ Justin Goodwin ⋅ Rajmonda Caceres ⋅ Robin Walters
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Dian Wang ⋅ Jung Yeon Park ⋅ Neel Sortur ⋅ Lawson Wong ⋅ Robin Walters ⋅ Robert Platt
Large language models partially converge toward human-like concept organization
Jonathan Gabel Christiansen ⋅ Mathias Gammelgaard ⋅ Anders Søgaard
Cayley Graph Propagation
Joseph Wilson ⋅ Petar Veličković
Curvature Fields from Shading Fields
Xinran Han ⋅ Todd Zickler
A Comparison of Equivariant Vision Models with ImageNet Pre-training
David Klee ⋅ Jung Yeon Park ⋅ Robert Platt ⋅ Robin Walters
Learning Symmetrization for Equivariance with Orbit Distance Minimization
Dat Nguyen ⋅ Jinwoo Kim ⋅ Hongseok Yang ⋅ Seunghoon Hong
Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach
Giovanni Luca Marchetti ⋅ Gabriele Cesa ⋅ Kumar Pratik ⋅ Arash Behboodi