NeurIPS 2025 Past Other
NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations
NeurReps 2025
- Submission deadline
- Sep 11, 2025, 04:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (121)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Comparative Empirical Study of Relative Embedding Alignment in Neural Dynamical System Forecasters
-
A Dendritic-Inspired Network Science Generative Model for Topological Initialization of Connectivity in Sparse Artificial Neural Networks
-
A New Perspective for Graph Learning Architecture Design: Linearize Your Depth Away
-
A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
-
Activation Matching for Explanation Generation and Circuit Discovery
-
Affect2Act: Graph Attention Networks for Emotion-Informed Decision Making
-
An Analytical Framework for Multi-Area Balanced Networks
-
An Information-Geometric View of the Platonic Hypothesis
-
Any-Subgroup Equivariant Networks via Symmetry Breaking
-
Balancing Fairness and Accuracy in Graph Learning via Fairness-Constrained Rewiring
-
Beyond I-Con: A Roadmap for Representation Learning Loss Discovery
-
Beyond Parallelism: Synergistic Computational Graph Effects in Multi-Head Attention
-
Beyond Pixels: A Differentiable Pipeline for Probing Neuronal Selectivity in 3D
-
Bispectral OT: Dataset Comparison using Symmetry-Aware Optimal Transport
-
Boundary Guidance for Efficient 3D CT Vision–Language Reasoning
-
Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
-
Cannistraci-Hebb Training of Convolutional Neural Networks
-
CAP$_{\mathcal{M}}$ : Curvature-Aware Pulling on Riemannian Manifolds
-
Causal Geometry of Batch Size and Generalisation
-
Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
-
Complete Characterization of Gauge Symmetries in Transformer Architectures
-
Composed Program Induction with Latent Program Lattice
-
Compositional Symmetry as Compression: Lie‑Pseudogroup Structure in Algorithmic Agents
-
Context-Dependent Manifold Learning in Dynamical Systems: A Neuromodulated Constrained Autoencoder Approach
-
Contrast inversion reveals hierarchical asymmetries of contrast processing in biological and artificial vision
-
Contrastive Learning with Latent Tension Regularization for Tight Orbits
-
Covering Relations in the Poset of Combinatorial Neural Codes
-
Curvature Dynamic Black-box Attack: revisiting adversarial robustness via dynamic curvature estimation
-
Curvature Estimation on Data Manifolds via Diffusion-augmented Sampling
-
Curvature Meets Bispectrum: A Correspondence Theory for Transformer Gauge Invariants
-
Data Augmentation: A Fourier Analysis Perspective
-
Deep neural network model of sound localization replicates “what” and “where” representations in auditory cortex
-
DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
-
Dimensionality of population-level latent mechanisms encoding spatial representations
-
Do Masked Autoencoders Learn a Human-Like Geometry of Neural Representation? Divergence and Convergence Across Brains and Machines During Naturalistic Vision
-
Do traveling waves make good positional encodings?
-
Dual-Stream EEG Decoding for 3D Visual Perception
-
ECoNets: Rotation Equivariant Contrail Detection Neural Networks in Satellite Imagery
-
Emergent Riemannian geometry over learning discrete computations on continuous manifolds
-
Equivariance by Local Canonicalization: A Matter of Representation
-
Event2Vec: A Geometric Approach to Learning Composable Representations of Event Sequences
-
Exact Learning Dynamics of In-Context Learning in Linear Transformers and Its Application to Non-Linear Transformers
-
Exploring Learnability in Dynamical Stochastic Networks: A Field-Theoretic Approach
-
Factorized Prefrontal Geometry of Goal and Uncertainty Explains Flexible yet Stable Human Goal Pursuit
-
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
-
Filter Equivariant Functions: A symmetric account of length-general extrapolation on lists
-
Flow Equivariant World Models: Structured Dynamics Outside the Field of View
-
From Extrapolation to Generalization: How Conditioning Transforms Symmetry Learning in Diffusion Models
-
From Finite to Infinite Groups: A Polynomial-Time Algorithm for Learning with Exact Invariances
-
Gauge Fiber Bundle Geometry of Transformers
-
Generalizable Representation Geometry for Grating Stimuli in Primary Visual Cortex and Artificial Neural Networks
-
Geometric Priors for Generalizable World Models via Vector Symbolic Architecture
-
Geometry matters: insights from Ollivier Ricci Curvature and Ricci Flow into representational alignment
-
Graph Mixing Additive Networks
-
Group Convolutional Self-Attention for Roto-Translation Equivariance in ViTs
-
Hilbert geometry of the symmetric positive-definite bicone
-
Homological Representation Learning for Molecular Graphs
-
How does training shape the Riemannian geometry of neural network representations?
-
Inferring dynamical features from neural data through joint learning of latents factors and weights
-
K-theoretic Persistent Cohomology
-
Koopman Autoencoders Learn Neural Representation Dynamics
-
Learning from Frustration: Torsor CNNs on Graphs
-
Learning rate collapse prevents training recurrent neural networks at scale
-
Learning representations on Lp hyperspheres: The equivalence of loss functions in a MAP approach
-
LFMA: Parameter-Efficient Fine-Tuning via Layerwise Fourier Masked Adapter with Top-k Frequency Selection
-
Local Predictions, Global Learning: Radial Basis Function Networks for Spatially-Aware Predictive Coding
-
Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation
-
Mapping neural representations of topologically non-trivial spaces
-
MAPS: A Dataset for Controlled Probing of Representational Topology in Vision Models
-
Measure Before You Look: Grounding Embeddings Through Manifold Metrics
-
Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
-
Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedback
-
Mixed Monotonicity Reachability Analysis of Neural ODE: A Trade-Off Between Tightness and Efficiency
-
Model manifold analysis suggests the human visual brain is less like an optimal classifier and more like a feature bank
-
Model Transferability Informed by Embedding’s Topology
-
Modeling Human Vision with Differential Geometry
-
Neural Fields Meet Attention
-
Neural Manifold Geometry Encodes Feature Fields
-
Neurosymbolic Rabbit Brain: Fractal Attractor Geometry for Neural Representations
-
On a Geometry of Interbrain Networks
-
On neural circuits of working memory sequence permutation: optimizing circuit architectures via Cayley graphs
-
On the geometry of recurrent spiking networks
-
On the Impact of Topological Regularization on Geometrical and Topological Alignment in Autoencoders: An Empirical Study
-
On Uncertainty Calibration for Invariant Functions
-
Persistent Homology Distances for Comparing Disease-Filtered Structural Connectomes
-
Poisson-Algebraic Parallel Scan: A Fast Symplectic Framework for Neural Hamiltonians
-
Provable Low-Frequency Bias of In-Context Learning of Representations
-
Quantifying information stored in synaptic connections rather than in firing activities of neural networks
-
Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization
-
REM3DI: Learning smooth, chiral 3D molecular representations from equivariant atomistic foundation models
-
Representational Homomorphism Error Predicts Compositional Generalization In Language Models
-
Response Patterns to Rotation Angle in a Rotation Pretext Task Vary Across Datasets and Architectures: An Observation and a Negative Result
-
Saliency Thresholds in Neural Code and its Relation to the Power-Law, Gaussian, and Lambert W Function
-
Sample Efficient Offline RL via T-symmetry Enforced Latent State-Stitching
-
Scalable GPU-Accelerated Euler Characteristic Curves: Optimization and Differentiable Learning for PyTorch
-
Self-Supervised Learning from Structural Invariance
-
Shape-Based Features Complement CLIP Features and Features Learned from Voxels in 3D Object Classification
-
Shaping Latent Geometry with Noise-Injected Hopfield Dynamics
-
Sheaf Cohomology of Linear Predictive Coding Networks
-
Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks
-
SRTD: A Symmetric Divergence for Interpretable Comparison of Representation Topology
-
Symmetry as Intervention; Causal Estimation with Data Augmentation
-
Symmetry-Regularized Learning of Continuous Attractor Dynamics
-
The Binding Problem in Vision Models: Geometric, Functional, and Behavioral Approaches
-
The Cue or not the Cue? A Mechanistic Study of Memory Mechanisms in RNNs
-
The Geometry and Topology of Modular Addition Representations
-
The Geometry of Cortical Computation: Manifold Disentanglement and Predictive Dynamics in VCNet
-
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
-
The Human Brain as a Combinatorial Complex
-
The Representations of Deep Neural Networks Trained on Dihedral Group Multiplication
-
Theoretical Analysis of HyperCube Objective for Group Representation Learning
-
Time-Resolved Circuit Discovery in RNNs via Windowed Causal Interventions and Local Linearization
-
Topological Neural Data Analysis with Behavioral Constraint
-
Topological Signatures of Altered Brain Network Centrality in ADHD: A TDA Mapper Study
-
Towards the Identification of Latent Structures in Language Embeddings
-
Tracking Memorization Geometry throughout the Diffusion Model Generative Process
-
Transformers Represent Causal Abstractions
-
Unified Generative Latent Representation for Functional Brain Graphs
-
Unifying Global Topology Manifolds and Local Persistent Homology for Data Pruning
-
Unifying Regression and Uncertainty Quantification with Contrastive Spectral Representation Learning
-
Why all roads don’t lead to Rome: Representation geometry varies across the human visual cortical hierarchy