NeurIPS 2025PastOther
2nd edition of Frontiers in Probabilistic Inference: Learning meets Sampling
FPI-NEURIPS2025
- Submission deadline
- Sep 3, 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 (66)
Fetched from OpenReview (v2) on 2026-06-10.
$p\textrm{-less}$ Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
A Gradient Flow approach to Solving Inverse Problems with Latent Diffusion Models
A Priori Sampling of Transition States with Guided Diffusion
A Sampling-Based Domain Generalization Study with Diffusion Generative Models
A Unification of Discrete, Gaussian, and Simplicial Diffusion
Adaptive Destruction Processes for Diffusion Samplers
Adaptive Inference Scaling via Monte Carlo Sampling
An Eulerian Perspective on Straight-Line Sampling
Bring fusion energy closer: challenges for probabilistic inference in the multiphysics, multiscale environment of fusion devices
Can We Estimate The Entropy Of Arbitrary Distributions Known Up To A Normalization Constant?
Categorical Flow Matching via Simplex-to-Euclidean Bijections
Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
Combined Representation and Generation with Diffusive State Prediction Information Bottleneck
Compression Meets Sampling: On Energy-Efficient Random Variate Generation
Constrained Flow Optimization via Sequential Fine-Tuning for Molecular Design
Control Consistency Losses for Diffusion Bridges
Convergences guarantees of GFlowNets
Counterdiabatic Hamiltonian Monte Carlo
Data Generation without Function Estimation
Data-to-Energy Stochastic Dynamics
DDS-E-Sim: A Transformer-based Probabilistic Generative Framework for Simulating Error-Prone DNA Sequences for DNA Data Storage
Discrete Stochastic Localization for Non-Autoregressive Generation
e-SimFT: Pareto-Optimal Sampling of Generative Design Models Fine-tuned with Simulation Feedback
Energy-Based Physics-Informed Diffusion Transformers Sampling for Time Series Forecasting
Enhancing Diversity in Large Language Models via Determinantal Point Processes
Entangled Schrödinger Bridge Matching
Frame-based Equivariant Diffusion Models for 3D Molecular Generation
From Predictors to Samplers via the Training Trajectory
Generalised Flow Maps on Riemannian Manifolds
GNN-Guided Block Selection in Gibbs MCMC
Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo
Inference-time alignment of language models by importance sampling on pre-logit space
Infinite Dimensional Adjoint Sampler: Scalable Sampling on Function Spaces
Ising Machines for Model Predictive Path Integral-Based Optimal Control
Latent Spaces for Langevin Dynamics
Learning Boltzmann Generators via Constrained Mass Transport
Learning Discrete Distributions from Metastable Data via Pseudo-Likelihood
Learning Paths for Dynamic Measure Transport: A Control Perspective
Learning Velocity Prior-Guided Hamiltonian-Jacobi Flows with Unbalanced Optimal Transport
Machine-Learned Sampling of Conditioned Path Measures
Model Agnostic Conditioning of Boltzmann Generators for Peptide Cyclization
moPPIt-v3: Motif-Specific Peptides Generated via Multi-Objective-Guided Discrete Flow Matching
Multi-Objective Nanobody Design via Masked Discrete Diffusion with Simplex Refinement
Multimarginal Flow Matching with Adversarially Learnt Interpolants
Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
Ordered Diversity Sampling for Text
Particle Monte Carlo methods for Lattice Field Theory
Pokie: Posterior Accuracy and Model Comparison
Probabilistic Modeling of Antibody Structural Dynamics
Relative Trajectory Balance is equivalent to Trust-PCL
Robust Multi-task Modeling for Bayesian Optimization via In-Context Learning
Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
Sampling from Energy distributions with Target Concrete Score Identity
Sampling Strategies for Transformer-Based Mechanism Synthesis
ScooBDoob: Schrödinger Bridge with Doob’s h-Transform for Molecular Dynamics
Solving Inverse Problems with Stochastic Interpolants: Self-Consistent Generative Modeling from Corrupted Data
Steering Pretrained Drafters during Speculative Decoding
Token-Level Guided Discrete Diffusion for Membrane Protein Design
Tokenised Flow Matching for Hierarchical Simulation Based Inference
torchgfn: A PyTorch GFlowNet library
Towards Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Towards Integrating Uncertainty for Domain-Agnostic Segmentation
Uncertainty Weighted Deep Ensemble to Enhance Protein Property Prediction
Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation
Variational Entropy Search is Just 1D Regression
Weighted Conditional Flow Matching