NeurReps @ NeurIPS 2023

53 papers

Top Research Directions

Research directions most represented by NeurReps @ NeurIPS 2023 papers.

Hyperbolic Embeddings for Hierarchical Representation Learning 3
Soft and Adaptive Equivariance for Imperfect Symmetries 2
Comparing Neural Representations Through Relational Geometry 2
Permutation Symmetry and Alignment in Weight Space 2
Geometric Equivariance in 3D Molecular Deep Learning 2
Neural Network Weights as a Data Modality 1
Breaking the Homogeneity Assumption in Deep Learning Theory 1
Unifying Self-Supervised Learning via Mutual Information Maximization 1
Unifying Self-Supervised Learning via Spectral and Information Theory 1
Scale Equivariance through Bias Free Neural Architectures 1
Deep Learning on Riemannian Manifolds 1
Matryoshka Representation Learning 1
How Neural Populations Encode Probability Distributions 1
Relaxing Symmetry Constraints for Expressive Geometric Deep Learning 1
Balancing Diversity and Semantic Fidelity in Data Augmentation 1

Top Authors

AuthorPapers
Mikail Khona4
Robin Walters4
Emanuele Rodolà3
Pietro Lio3
Anders Søgaard2
Arash Behboodi2
Arna Ghosh2
Blake Aaron Richards2
Gabriele Cesa2
Ila R Fiete2
Irene Cannistraci2
Isao Ishikawa2
Jung Yeon Park2
Kumar Krishna Agrawal2
Luca Moschella2
Masahiro Ikeda2
Neel Sortur2
Petar Veličković2
Robert Platt2
Rylan Schaeffer2

Impactful Papers

Papers from NeurReps @ NeurIPS 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
The Variability of Representations in Mice and Humans Changes with Learning, Engagement, and Attention
Visual Scene Representation with Hierarchical Equivariant Sparse Coding

« prev Page 2/2