Derives closed-form posterior covariance for flow matching from divergence of velocity field, enabling post-hoc uncertainty on pre-trained models including one-step generators.
hub Mixed citations
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
Mixed citation behavior. Most common role is background (69%).
94
Pith papers citing it
Background
69% of classified citations
abstract
A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic processes called stochastic interpolants to bridge any two probability density functions exactly in finite time. These interpolants are built by combining data from the two prescribed densities with an additional latent variable that shapes the bridge in a flexible way. The time-dependent density function of the interpolant is shown to satisfy a transport equation as well as a family of forward and backward Fokker-Planck equations with tunable diffusion coefficient. Upon consideration of the time evolution of an individual sample, this viewpoint leads to both deterministic and stochastic generative models based on probability flow equations or stochastic differential equations with an adjustable level of noise. The drift coefficients entering these models are time-dependent velocity fields characterized as the unique minimizers of simple quadratic objective functions, one of which is a new objective for the score. We show that minimization of these quadratic objectives leads to control of the likelihood for generative models built upon stochastic dynamics, while likelihood control for deterministic dynamics is more stringent. We also construct estimators for the likelihood and the cross entropy of interpolant-based generative models, and we discuss connections with other methods such as score-based diffusion models, stochastic localization, probabilistic denoising, and rectifying flows. In addition, we demonstrate that stochastic interpolants recover the Schr\"odinger bridge between the two target densities when explicitly optimizing over the interpolant. Finally, algorithmic aspects are discussed and the approach is illustrated on numerical examples.
hub tools
citation-role summary
background 11
method 5
citation-polarity summary
claims ledger
- abstract A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic processes called stochastic interpolants to bridge any two probability density functions exactly in finite time. These interpolants are built by combining data from the two prescribed densities with an additional latent variable that shapes the bridge in a flexible way. The time-dependent density function of the interpolant is shown to satisfy a transport e
co-cited works
representative citing papers
FMRG reformulates guidance as deterministic optimal control, deriving a single-trajectory method using the flow map that matches or exceeds baselines on reward-guided generation and inverse problems with 3 NFEs at text-to-image scale.
Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.
Flow-GRPO is the first online RL method for flow matching models, raising GenEval accuracy from 63% to 95% and text-rendering accuracy from 59% to 92% with little reward hacking.
A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
Flow models reach 99.2% Sudoku accuracy in 7 passes and 96.1% on out-of-distribution Sudoku-Extreme by selecting dynamically stable candidates and training with self-conditioning plus DPO to avoid failed outputs.
DiSI disentangles stochastic interpolants into separate generation and regression paths, allowing controllable transitions between regression and generative image restoration with a unified few-step sampler.
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
Non-monotonic sampling schedules never improve upon monotonic baselines in diffusion models, with performance gaps ranging from substantial to negligible depending on the denoiser.
TMPO uses Softmax Trajectory Balance to match policy probabilities over multiple trajectories to a Boltzmann reward distribution, improving diversity by 9.1% in diffusion alignment tasks.
FLUX reconstructs longitudinal transport and recovers interpretable regime structure from unpaired biological snapshots by combining geometry-aware flow matching with mixture-of-experts velocity decomposition.
First-order asymptotic expansions of weak and Fréchet discretization errors in diffusion sampling are derived, explicit under Gaussian data through covariance geometry and robust to other data geometries.
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
ABC enables any-subset autoregressive generation of continuous stochastic processes via non-Markovian diffusion bridges that track physical time and allow path-dependent conditioning.
ALMC-ODE uses annealed Langevin Monte Carlo with Jarzynski reweighting to produce a low-variance velocity estimator for flow ODE sampling, with an O(1/n) MSE bound and superior performance on multimodal benchmarks.
ScoRe-Flow achieves decoupled mean-variance control in stochastic flow matching by deriving a closed-form score for drift modulation plus learned variance, yielding faster RL convergence and higher success rates on locomotion and manipulation benchmarks.
GVCC achieves the lowest LPIPS on UVG at bitrates down to 0.003 bpp by encoding stochastic innovations in a marginal-preserving stochastic process derived from a pretrained rectified-flow video model, with 65% LPIPS reduction over DCVC-RT.
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.
SCSI iteratively refines a self-consistent transport map to invert black-box corruptions and enable generative modeling of clean data.
citing papers explorer
-
Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision
x0-supervision or equivalent loss re-weighting accelerates convergence in controllable diffusion models while improving visual quality and conditioning accuracy.
-
Monte Carlo Event Generation with Continuous Normalizing Flows
Continuous normalizing flows improve unweighting efficiency in Monte Carlo event generation for high-jet-multiplicity collider processes by factors up to 184, with wall-time gains of about ten when combined with coupling-layer flows.
-
Flow Matching is Adaptive to Manifold Structures
Flow matching achieves near-minimax optimal statistical consistency for manifold-supported distributions, with convergence rates governed by intrinsic dimension and smoothness rather than ambient dimension.
-
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
Continuous flows on token embeddings with flow-map distillation produce one-step language models whose quality exceeds recent 8-step discrete diffusion baselines on LM1B and OpenWebText.
-
World Action Models are Zero-shot Policies
DreamZero uses a 14B video diffusion model as a World Action Model to achieve over 2x better zero-shot generalization on real robots than state-of-the-art VLAs, real-time 7Hz closed-loop control, and cross-embodiment transfer with 10-30 minutes of data.
-
Protein Autoregressive Modeling via Multiscale Structure Generation
PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and zero-shot conditional outputs.
-
HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts
HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.
-
RenderFlow: Single-Step Neural Rendering via Flow Matching
RenderFlow replaces iterative diffusion with flow matching for deterministic single-step neural rendering that achieves near real-time photorealistic quality and extends to inverse rendering via an adapter module.
-
Residual Diffusion Bridge Model for Image Restoration
RDBM reformulates generalized diffusion bridge SDEs to use distribution residuals for adaptive noise modulation, unifying prior bridge models as special cases and achieving SOTA on image restoration tasks.
-
VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
VFM-VAE uses a frozen VFM directly as LDM tokenizer via a custom decoder, reaching gFID 2.22 in 80 epochs and 1.62 after 640 epochs.
-
Flow Matching for Measure Transport and Feedback Stabilization of Control-Affine Systems
Introduces flow matching for measure transport in control-affine systems and a complementary noising-time-reversal method for stabilization, with numerical examples on linear and nonlinear cases.
-
Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
Energy-Weighted Flow Matching reformulates conditional flow matching with importance sampling to enable continuous normalizing flows to model Boltzmann distributions from energy evaluations alone, with iterative and annealed variants showing competitive performance on benchmarks.
-
Latent Stochastic Interpolants
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
-
Fast Kernel-Space Diffusion for Remote Sensing Pansharpening
KSDiff generates convolutional kernels in kernel space using low-rank core tensor and factor generators with multi-head attention for fast, high-quality pansharpening.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
-
Improved DDIM Sampling with Moment Matching Gaussian Mixtures
Moment-matched GMM kernels in DDIM yield lower FID and higher IS than Gaussian kernels at small sampling steps on CelebA-HQ, FFHQ, ImageNet, and Stable Diffusion tasks.
-
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
FREUD applies rectified flow transformers with frame-wise encoding and a unified decoder to achieve state-of-the-art probabilistic precipitation nowcasting on the SEVIR benchmark.
-
Measure-to-measure Regression with Transformers
Formalizes nonlinear M2M regression and introduces transformer architectures as static maps and dynamic velocity fields between probability measures, tested on synthetic, particle, and organoid datasets.
-
Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction
A generative solver separates data-driven prior learning from inference-time enforcement of conservation laws using martingale-regularized score matching and physics-informed sampling for stable field reconstruction.
-
Drift Flow Matching
Drift Flow Matching connects direct transport maps from Drift Models with flow-based iterative refinement to enable adaptive computation in generative modeling.
-
When Latent Geometry Is Not Enough: Draft-Conditioned Latent Refinement for Non-Autoregressive Text Generation
Latent geometry metrics fail to ensure good token decoding in non-autoregressive text models; decoder recoverability and start distribution quality are the necessary evaluation criteria.
-
Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
SharpEuler estimates a sharpness profile via finite differences on calibration trajectories, smooths it, and applies a quantile transform to generate adaptive timestep grids that improve Euler sampling quality in flow matching models at fixed budgets.
-
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Bayesian inverse problem with diffusion model priors for CML-based rain field reconstruction outperforms baselines by preserving rainfall statistics better than Gaussian processes.
-
Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data
Neural posterior estimation trained on GPU-simulated radar data enables calibrated probabilistic inversion of terrain parameters and transfers to real Mars radar profiles.
-
PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling
PRiMeFlow applies flow matching in gene expression space with a U-Net velocity field and pretraining-finetuning to model perturbation-induced heterogeneity, showing strong benchmark performance on PerturBench and the ARC Virtual Cell Challenge.
-
Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models
E-Bridge approximates low-cost geodesic trajectories in diffusion bridges for image restoration by using shorter time horizons, entropy-regularized starts mixing degraded images with noise, and consistency-model single-step mapping, achieving SOTA results with one or few steps.
-
Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
-
Assured autonomy: How operations research powers and orchestrates generative AI systems
The authors develop a conceptual framework for assured autonomy in generative AI by using flow-based models for auditable generation and adversarial robustness for operational safety, repositioning operations research as a system architect.
-
Stability of the Kim--Milman flow map
The paper characterizes stability of the Kim-Milman flow map with respect to target measure variations measured in relative Fisher information.
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
-
Simplifying Flow Matching Transformations with Low-Rank Mixture Models
MPPCA mixtures as latent densities for normalizing flows reduce transformation complexity via better KL alignment, yielding faster convergence and better generation than standard normal baselines.
-
Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation
UCD adjusts diffusion-based 3D molecular graph generation to handle epistemic uncertainty, improving sample quality and reaching new benchmark performance.
-
Flow Matching for Convective-Scale Precipitation Downscaling
Flow matching produces better spatial structure than diffusion models for convective precipitation downscaling but underestimates heavy rainfall amounts.
-
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
One-step pixel-MeanFlow models recover key galaxy morphology statistics at orders-of-magnitude lower computational cost than standard DDPM sampling while remaining weaker on fine-grained structure.
-
A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models
Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.
-
Venom: A PyTorch Generative Modeling Toolkit
Venom is an educational PyTorch toolkit that packages multiple generative modeling families under a single MNIST-first interface with reproducible scripts and tutorials.
-
Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference
Simulation-based inference uses neural networks trained on simulations to enable parameter inference in cosmology and astrophysics where traditional likelihood calculations are intractable.
-
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
A mathematical review of flow matching techniques for generative models, showing characterizations via couplings, kernels, and processes, with application to inverse problems.
-
Introduction to Stochastic Differential Equations for Generative Machine Learning: A Variational Perspective
An expository tutorial deriving the ELBO for SDE-based generative models and presenting diffusion, score, and flow matching as variational parameterizations illustrated on a 1D example.
- MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems
- Generative models for decision-making under distributional shift
- Pathwise Learning of Stochastic Dynamical Systems with Partial Observations
- The Principles of Diffusion Models