NeurIPS 2024PastOther
NeurIPS 2024 Workshop on Symmetry and Geometry in Neural Representations
NeurReps 2024
- Submission deadline
- Sep 24, 2024, 12:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (61)
Fetched from OpenReview (v2) on 2026-06-10.
A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing
A minimalistic representation model for head direction system
A New Geometric Approach of Adaptive Neighborhood Selection for Classification
Adversarially-robust representation learning through spectral regularization of features
An Information Parsimony Perspective on Probabilistic Symmetries
BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration
CantorNet: A Sandbox for Testing Topological and Geometrical Measures
Certifying Robustness via Topological Representations
Communication subspaces align with training in ANNs
Connecting Neural Models Latent Geometries with Relative Geodesic Representations
Constrained Belief Updating and Geometric Structures in Transformer Representations
Convergence of Manifold Filter-Combine Networks
Counterfactual Explanations via Riemannian Latent Space Traversal
Does equivariance matter at scale?
Does Maximizing Neural Regression Scores Teach Us About The Brain?
Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
Efficient Subgraph GNNs via Graph Products and Coarsening
Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification
EqNIO: Subequivariant Neural Inertial Odometry
Exploring Geometric Representational Alignment through Ollivier-Ricci Curvature and Ricci Flow
Galois features: Nearly-complete invariants on symmetric matrices
Geometric Machine Learning on EEG Signals
Geometric Signatures of Compositionality Across a Language Model’s Lifetime
Graph Neural Networks Uncover Geometric Neural Representations in Reinforcement-Based Motor Learning
Hamiltonian Matching for Symplectic Neural Integrators
Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance
Hidden Holes - topological aspects of language models
Improving Deep Learning Speed and Performance through Synaptic Neural Balance
In-Context Symmetries: Self-Supervised Learning through Contextual World Models
Invariant Graphon Networks: Approximation and Cut Distance
Klein Model for Hyperbolic Neural Networks
Knowledge Distillation for Teaching Symmetry Invariances
Learning Effective NeRFs and SDFs Representations with 3D GANs for Object Generation
Learning Symmetric Contexts for Anomaly Detection
Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
MNIST-Nd: a set of naturalistic datasets to benchmark clustering across dimensions
Modeling dynamic neural activity by combining naturalistic video stimuli and stimulus-independent latent factors
Multi-task Learning yields Disentangled World Models: Impact and Implications
Neural Network Symmetrisation in Concrete Settings
Neural Representational Geometry of Concepts in Large Language Models
On Layer-wise Representation Similarity: Application for Multi-Exit Models with a Single Classifier
On Optimal Lifting to SE(2) in Equivariant Neural Networks
On the Reconstruction of Training Data from Group Invariant Networks
On the Ricci Curvature of Attention Maps and Transformers Training and Robustness
Probabilistic Nested Homogeneous Spaces for Dimensionality Reduction
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice
RelWire: Metric Based Rewiring
Rethinking Message Passing for Algorithmic Alignment
sa-SVAE: a Shared and Aligned Structured Variational Autoencoder for Extracting Behaviorally Relevant and Preserved Neural Dynamics Across Animals
Storing overlapping associative memories on latent manifolds in low-rank spiking networks
Structure Development in List Sorting Transformers
Structure Matters: Deciphering Neural Network's Properties from its Structure
Structured In-Context Task Representations
Supervised Quadratic Feature Analysis: An information geometry approach to dimensionality reduction
Symmetry-Aware Generative Modeling through Learned Canonicalization
Theoretical Insights into Line Graph Transformation on Graph Learning
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
Toward Understanding How the Data Affects Neural Collapse: A Kernel-Based Approach
Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs
Visualizing Loss Functions as Topological Landscape Profiles