ICML 2024 Past Generative models
ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling
ICML 2024 Workshop GRaM
- Submission deadline
- Jun 3, 2024, 20:00 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 (82)
Fetched from OpenReview (v2) on 2026-06-10.
-
(Deep) Generative Geodesics
-
3D Shape Completion with Test-Time Training
-
A Coding-Theoretic Analysis of Hyperspherical Prototypical Learning Geometry
-
A Geometric Framework for Understanding Memorization in Generative Models
-
A Simple and Expressive Graph Neural Network Based Method for Structural Link Representation
-
A Theoretical Formulation of Many-body Message Passing Neural Networks
-
Adaptive Sampling for Continuous Group Equivariant Neural Networks
-
Aligned Diffusion Models for Retrosynthesis
-
Alignment of MPNNs and Graph Transformers
-
All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
-
An Equivariant Flow Matching Framework for Learning Molecular Crystallization
-
Approximate natural gradient in Gaussian processes with non-log-concave likelihoods
-
Asynchrony Invariance Loss Functions for Graph Neural Networks
-
Bias-inducing geometries: exactly solvable data model with fairness implications
-
Bundle Neural Networks for message diffusion on graphs
-
Commute-Time-Optimised Graphs for GNNs
-
Consistency models with learned idempotent boundary conditions
-
Constructing gauge-invariant neural networks for scientific applications
-
CoordConformer: Heterogenous EEG datasets decoding using Transformers
-
Decoder ensembling for learned latent geometries
-
Decomposed Linear Dynamical Systems (dLDS) for identifying the latent dynamics underlying high-dimensional time-series
-
Dirac--Bianconi Graph Neural Networks - Enabling long-range graph predictions
-
E(n) Equivariant Message Passing Cellular Networks
-
Energy-based Hopfield Boosting for Out-of-Distribution Detection
-
Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification
-
Gaussian Process-Based Representation Learning via Timeseries Symmetries
-
Geometric algebra transformers for large 3D meshes via cross-attention
-
Geometric Wireless Simulation with Equivariant Transformers
-
Geometry Aware Deep Learning for Integrated Closed-shell and Open-shell Systems
-
Geometry Fidelity for Spherical Images
-
Geometry-Aware Autoencoders for Metric Learning and Generative Modeling on Data Manifolds
-
Geometry-informed Neural Networks
-
GLAudio Listens to the Sound of the Graph
-
Graph Convolutional Networks for Learning Laplace-Beltrami Operators
-
Improving Equivariant Networks with Probabilistic Symmetry Breaking
-
InfoNCE: Identifying the Gap Between Theory and Practice
-
Invertible Temper Modeling using Normalizing Flows and the Effects of Structure Preserving Loss
-
Joint Diffusion Processes as an Inductive Bias in Sheaf Neural Networks
-
Latent functional maps
-
Learning Diffeomorphic Lyapunov Functions from Data
-
Learning symmetries via weight-sharing with doubly stochastic tensors
-
Leveraging Topological Guidance for Improved Knowledge Distillation
-
Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space
-
Lorentzian Residual Neural Networks
-
Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design
-
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
-
Metric Learning for Clifford Group Equivariant Neural Networks
-
Mixed-Curvature Decision Trees and Random Forests
-
Multivector Neurons: Better and Faster O(n)-Equivariant Clifford GNNs
-
On Fairly Comparing Group Equivariant Networks
-
On The Local Geometry of Deep Generative Manifolds
-
On the Matter of Embeddings Dispersion on Hyperspheres
-
Path Complex Neural Network for Molecular Property Prediction
-
Permutation Tree Invariant Neural Architectures
-
Probabilistic World Modeling with Asymmetric Distance Measure
-
Relaxed Equivariant Graph Neural Networks
-
Revisiting Random Walks for Learning on Graphs
-
RIO-CPD: A Riemannian Geometric Method for Correlation-aware Online Change Point Detection
-
Scalable Local Intrinsic Dimension Estimation with Diffusion Models
-
SCENE-Net V2: Interpretable Multiclass 3D Scene Understanding with Geometric Priors
-
SE(3)-Hyena Operator for Scalable Equivariant Learning
-
SE3ET: SE(3)-Equivariant Transformer for Low-Overlap Point Cloud Registration
-
Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries
-
Sheaf Diffusion Goes Nonlinear: Enhancing GNNs with Adaptive Sheaf Laplacians
-
SINR: Equivariant Neural Vector Fields
-
Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs
-
Stitching Manifolds: Leveraging Interaction to Compose Object Representations into Scenes.
-
Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces
-
Temporal Graph Rewiring with Expander Graphs
-
The Geometry of Diffusion Models: Tubular Neighbourhoods and Singularities
-
The NGT200 Dataset - Geometric Multi-View Isolated Sign Recognition
-
The Price of Freedom: Exploring Tradeoffs between Expressivity and Computational Efficiency in Equivariant Tensor Products
-
Theoretical Analyses of Hyperparameter Selection in Graph-Based Semi-Supervised Learning
-
Topological and Dynamical Representations for Radio Frequency Signal Classification
-
Topology-Informed Graph Transformer
-
Towards General Geometries for Embedding Knowledge Graphs
-
Transferability for Graph Convolutional Networks
-
UHCone: Universal Hyperbolic Cone For Implicit Hierarchical Learning
-
Understanding Hallucinations in Diffusion Models through Mode Interpolation
-
Unsupervised Ground Metric Learning with Tree Wasserstein Distance
-
Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks
-
What Makes a Machine Learning Task a Good Candidate for an Equivariant Network?