ICLR 2025PastOther
Frontiers in Probabilistic Inference: Learning meets Sampling
FPI-ICLR2025
- Submission deadline
- Feb 12, 2025, 00:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (88)
Fetched from OpenReview (v2) on 2026-06-10.
A Probabilistic Approach to Self-Supervised Learning using Cyclical Stochastic Gradient MCMC
Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
Amortized Posterior Sampling with Diffusion Prior Distillation
An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Control
Approximate Posteriors in Neural Networks: A Sampling Perspective
Atomic Posterior Ensembles for Simulation-Based Inference
Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space
Beyond Schrödinger Bridges: A Least-Squares Approach for Learning Stochastic Dynamics with Unknown Volatility
Blink of an eye: a simple theory for feature localization in generative models
Breaking the Likelihood--Quality Trade-off in Diffusion Models by Merging Pretrained Experts
Can Transformers Learn Full Bayesian Inference In Context?
Clifford Group Equivariant Diffusion Models For 3D Molecular Generation
Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
Consistency Training with Physical Constraints
Continuously Tempered Diffusion Samplers
Controllable Generation via Locally Constrained Resampling
DDPS: Discrete Diffusion Posterior Sampling for Paths in Layered Graphs
Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo
Deep Optimal Sensor Placement for Black Box Stochastic Simulations
DeepRV: pre-trained spatial priors for accelerated disease mapping.
Distributionally Robust Posterior Sampling - A Variational Bayes Approach
Do You See the Shape? Diffusion Models for Noisy Radar Scattering Problems
Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluation
Efficient Asynchronize Stochastic Gradient Algorithm with Structured Data
Efficiently Warmstarting MCMC for BNNs
Electrostatics-based particle sampling and approximate inference
Ensemble Kalman Sampling and Diffusion Prior in Tandem: A Split Gibbs Framework
EQM-MPD: EQUIVARIANT ON-MANIFOLD MOTION PLANNING DIFFUSION
Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
Flat Posterior For Bayesian Model Averaging
Follow Hamiltonian Leader: An Efficient Energy-Guided Sampling Method
Generalised Parallel Tempering: Flexible Replica Exchange via Flows and Diffusions
Global-Order GFlowNets
Greed is Good: Guided Generation from a Greedy Perspective
Improving the evaluation of samplers on multi-modal targets
Inclusive KL Minimization: A Wasserstein-Fisher-Rao Gradient Flow Perspective
Inference-Time Prior Adaptation in Simulation-Based Inference via Guided Diffusion Models
Inherent Exploration via Sampling for Stochastic Policies
Iterative Importance Fine-tuning of Diffusion Models
LEAPS: A discrete neural sampler via locally equivariant networks
Learning Decision Trees as Amortized Structure Inference
Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks
Low Stein Discrepancy via Message-Passing Monte Carlo
Nested Slice Sampling
Neural Flow Samplers with Shortcut Models
Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Path Planning for Masked Diffusion Models with Applications to Biological Sequence Generation
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
Performance Evaluation of the Tensor Train Sampler in ML QUBO-based ADMET Classification
Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models
PINN-MEP: Continuous Neural Representations for Minimum Energy Path Discovery in Molecular Systems
Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization
Predicting 3D Structure by Latent Posterior Sampling
Probabilistic video prediction using conditional score diffusion
Provable Maximum Entropy Manifold Exploration via Diffusion Models
Quantification vs. Reduction: On Evaluating Regression Uncertainty
Quasi-random Multi-Sample Inference for Large Language Models
Recurrent Memory for Online Interdomain Gaussian Processes
Rethinking the Training of Diffusion Bridge Samplers: Losses and Exploration
Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
Sampling On Metric Graphs
Sampling through Algorithmic Diffusion in non-convex Perceptron problems
Scalable Equilibrium Sampling with Sequential Boltzmann Generators
Scalable Thompson Sampling via Ensemble++
Scaling Deep Learning Solutions for Transition Path Sampling
Score-Based Deterministic Density Sampling
Score-Debiased Kernel Density Estimation
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
Self-Supervised Learning Encodes Uncertainty
SFBD: A Method for Training Diffusion Models with Noisy Data
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
Single-Step Consistent Diffusion Samplers
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
Tensor-Train Unsupervised Image Segmentation
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
Uncertainty Quantification for Prior-Fitted Networks using Martingale Posteriors
Underdamped Diffusion Bridges with Applications to Sampling
Variational diffusion transformers for conditional sampling of supernovae spectra
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
von Mises-Fisher Sampling of GloVe Vectors
Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion
Wild posteriors in the wild
α-PFN: In-Context Learning Entropy Search