ICML 2024PastGenerative models
ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling
2nd SPIGM @ ICML
- Submission deadline
- May 28, 2024, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (116)
Fetched from OpenReview (v2) on 2026-06-10.
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
A Practical Diffusion Path for Sampling
Accelerating Best-of-N via Speculative Rejection
Accelerating NCE Convergence with Adaptive Normalizing Constant Computation
Accelerating statistical inferences in astrophysics with Neural Networks and Hamiltonian Monte Carlo
Aligned Diffusion Models for Retrosynthesis
All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
Amortized Active Causal Induction with Deep Reinforcement Learning
Amortized Probabilistic Detection of Communities in Graphs
Analyzing GFlowNets: Stability, Expressiveness, and Assessment
Assessing the Viability of Generative Modeling in Simulated Astronomical Observations
Bayesian Reward Models for LLM Alignment
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
Bidirectional Consistency Models
CADO: Cost-Aware Diffusion Solvers for Combinatorial Optimization through RL fine-tuning
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
Cell Morphology-Guided Small Molecule Generation with GFlowNets
Collective Variable Free Transition Path Sampling with Generative Flow Network
Color Style Transfer with Modulated Flows
Conditional Common Entropy for Instrumental Variable Testing and Partial Identification
Conditional Flow Matching for Time Series Modelling
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
Conformalized Credal Set Predictors
Continual Deep Learning on the Edge via Stochastic Local Competition among Subnetworks
Cross-modality Matching and Prediction of Perturbation Responses with Labeled Gromov-Wasserstein Optimal Transport
Demystifying amortized causal discovery with transformers
Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors
Diffusion Domain Expansion: Learning to Coordinate Pre-Trained Diffusion Models
Diffusion Models with Group Equivariance
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
DiMViS: Diffusion-based Multi-View Synthesis
Discrete Diffusion Posterior Sampling for Protein Design
Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
E-ProTran: Efficient Probabilistic Transformers for Forecasting
EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation
Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders
EigenVI: score-based variational inference with orthogonal function expansions
Energy-Free Guidance of Geometric Diffusion Models for 3D Molecule Inverse Design
Equivariant Flow Matching for Molecular Conformer Generation
EVCL: Elastic Variational Continual Learning with Weight Consolidation
Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
Fast yet Safe: Early-Exiting with Risk Control
Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable
From Graph Diffusion to Graph Classification
Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
Generative Autoencoding of Dropout Patterns
Generative Classifiers Avoid Shortcut Solutions
Generative Design of Decision Tree Policies for Reinforcement Learning
Generative Fractional Diffusion Models
GLAD: Improving Latent Graph Generative Modeling with Simple Quantization
Glauber Generative Model: Discrete Diffusion Models via Binary Classification
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
Identifying latent state transition in non-linear dynamical systems
Improving Consistency Models with Generator-Induced Coupling
Improving Flow Matching for Posterior Inference with Physics-based Controls
Improving GFlowNets for Text-to-Image Diffusion Alignment
Improving GFlowNets with Monte Carlo Tree Search
In-Context Learning with Topological Information for LLM-Based Knowledge Graph Completion
Incorporating Stability Into Flow Matching
Inferring Physiological Properties of Motor Neurons using Neural Posterior Estimation
Informed Meta-Learning
Investigating Generalization Behaviours of Generative Flow Networks
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Learnability of Parameter-Bounded Bayes Nets
Learning high-dimensional mixed models via amortized variational inference
Learning Latent Graph Structures and their Uncertainty
Lifted Residual Score Estimation
Many-to-many Image Generation with Auto-regressive Diffusion Models
Modelling Latent Dynamical Systems with Recognition-Parametrised Models
MONGOOSE: Path-wise Smooth Bayesian Optimisation via Meta-learning
Neural Ratio Estimators Meet Distributional Shift and Mode Misspecification: A Cautionary Tale from Strong Gravitational Lensing
Neurosymbolic Markov Models
Non-Parameteric Conformal Distributionally Robust Optimization
On Conditional Sampling with Joint Flow Matching
On the Expressive Power of Tree-Structured Probabilistic Circuits
Policy Gradients for Optimal Parallel Tempering MCMC
Predictive Uncertainties Based on Proper Scoring Rules
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
ProxyTune: Hyperparameter tuning through iteratively refined proxies
QGFN: Controllable Greediness with Action Values
Quantifying Aleatoric and Epistemic Uncertainty: A Credal Approach
Recursive Introspection: Teaching LLM Agents How to Self-Improve
Regression-Stratified Sampling for Optimized Algorithm Selection in Time-Constrained Tabular AutoML
Regularized Distribution Matching Distillation for One-step Unpaired Image-to-Image Translation
Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian Neural Networks
Reliability Thresholds for the Bethe Free Energy Approximation
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
RNA-FrameFlow for de novo 3D RNA Backbone Design
Rule-Enhanced Graph Learning
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models
Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval
scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data
Simple and Effective Masked Diffusion Language Models
Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices
SOLMformer - Incorporating Sequence and Observation Level Metadata for Categorical Time Series Modeling
Stabilizing the Training of Consistency Models with Score Guidance
Stein Variational Newton Neural Network Ensembles
Stochastic Concept Bottleneck Models
Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
Teaching dark matter simulations to speak the halo language
Test-Time Adaptation with State-Space Models
The Convolution-Closed Hurdle Motif With an Application to Tensor Decomposition
The GAN is dead; long live the GAN! A Modern Baseline GAN
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
Transferable Reinforcement Learning via Generalized Occupancy Models
Transformer Conformal Prediction for Time Series
Transformer Neural Autoregressive Flows
Transformers with Stochastic Competition for Tabular Data Modelling
Tuning-Free Alignment of Diffusion Models with Direct Noise Optimization
Upper Error Bounds for Score-Based Inverse Problem Solving in Imaging
Variance reduction of diffusion model's gradients with Taylor approximation-based control variate
Variational Inference with Censored Gaussian Process Regressors
von Mises Quasi-Processes for Bayesian Circular Regression
Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion