Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
super hub Canonical reference
Score-Based Generative Modeling through Stochastic Differential Equations
Canonical reference. 76% of citing Pith papers cite this work as background.
409
Pith papers citing it
Background
76% of classified citations
abstract
Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by slowly removing the noise. Crucially, the reverse-time SDE depends only on the time-dependent gradient field (\aka, score) of the perturbed data distribution. By leveraging advances in score-based generative modeling, we can accurately estimate these scores with neural networks, and use numerical SDE solvers to generate samples. We show that this framework encapsulates previous approaches in score-based generative modeling and diffusion probabilistic modeling, allowing for new sampling procedures and new modeling capabilities. In particular, we introduce a predictor-corrector framework to correct errors in the evolution of the discretized reverse-time SDE. We also derive an equivalent neural ODE that samples from the same distribution as the SDE, but additionally enables exact likelihood computation, and improved sampling efficiency. In addition, we provide a new way to solve inverse problems with score-based models, as demonstrated with experiments on class-conditional generation, image inpainting, and colorization. Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.89 and FID of 2.20, a competitive likelihood of 2.99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
hub tools
citation-role summary
background 71
method 17
baseline 3
other 1
citation-polarity summary
claims ledger
- abstract Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by slowly removing the noise. Crucially, the reverse-time SDE depends only on the time-dependent gradient field (\aka, score) of the perturbed data distribution. By leveraging advances in score-based generative modeling, we can accurately estimate
authors
co-cited works
representative citing papers
A-CODE presents a fully atomic one-stage multimodal diffusion model for protein co-design that claims superior unconditional generation performance over prior one- and two-stage models plus a tenfold success-rate gain on hard binder-design tasks.
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.
The García-Pintos feedback Hamiltonian equals the score function of the quantum trajectory distribution, linking quantum feedback to diffusion-model reversal.
Diffusion sampling from d-dimensional distributions requires at least ~sqrt(d) adaptive score queries when score estimates have polynomial accuracy.
OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.
Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
ASTRA reframes transition-state search as guided diffusion inference that samples the isodensity surface between metastable basins and converges to first-order saddles via score differences and physical forces.
MF-PID turns independent diffusion samples into mean-field interacting agents, proving that quadratic interactions yield exact linear mean interpolation and delivering 19-24% energy savings in demand-response control.
Föllmer processes are variationally optimal among generative diffusions because they minimize the impact of drift estimation error on path-space KL divergence, rendering different interpolation schedules statistically equivalent.
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.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
DDIMs construct non-Markovian diffusion processes that share DDPM training objectives but allow much faster reverse sampling, demonstrated empirically at 10-50x wall-clock speedup.
Hybrid simulation and non-Euclidean elasticity theory demonstrate that clathrin coats develop adaptive rigidity and memory during growth, producing flat, stalled, or closed outcomes through two energy-landscape gates and matching experiments without fitted parameters.
Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
CORDEX-ML-Bench benchmarks 40 ML models for climate downscaling and finds generative models outperform deterministic ones on precipitation while historically trained models underestimate future climate signals.
QMC applied to Euler-Maruyama yields faster sampling-error decay than Monte Carlo, and the new MSTG method based on exact simulation achieves super-exponential truncation-error decay that sharply reduces integration dimension.
STREAM decouples text and music conditioning in a diffusion transformer via AdaLN for structure and BEAM for beats, plus new Motorica++ dataset and editability metrics, claiming SOTA music alignment with preserved semantics.
Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
Chameleon proposes the first large-scale cross-domain compositing dataset and a disentangled encoder plus gated diffusion transformer that outperforms prior in-domain and cross-domain methods on plausibility and fidelity.
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
Spectral Guidance learns singular functions via self-supervised objective to project guidance signals onto diffusion sampling trajectories, enabling stable control without retraining or backpropagation and improving CIFAR-10 accuracy by 37 points with 4x faster sampling.
Presents a controlled vector field framework for continuous generative modeling where velocity is formed from fixed bracket-generating fields modulated by scalar controls, with an expressivity principle under controllability assumptions.
citing papers explorer
-
Fisher Decorator: Refining Flow Policy via a Local Transport Map
Fisher Decorator refines flow policies in offline RL via a local transport map and Fisher-matrix quadratic approximation of the KL constraint, yielding controllable error near the optimum and SOTA benchmark results.
-
CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization
CrossFlowDG bridges the modality gap in domain generalization by learning a continuous transformation that moves image embeddings to matching text embeddings using noise-free cross-modal flow matching.
-
Frequency-Aware Flow Matching for High-Quality Image Generation
FreqFlow introduces frequency-aware conditioning and a two-branch architecture to flow matching, reaching FID 1.38 on ImageNet-256 and outperforming DiT and SiT.
-
DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
RTR-DiT distills a bidirectional DiT teacher into an autoregressive few-step model using Self Forcing and Distribution Matching Distillation, plus a reference-preserving KV cache, to enable stable real-time text- and reference-guided video stylization.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
VGA-Bench creates a three-tier taxonomy, 1,016-prompt dataset of 60k+ videos, and three multi-task neural models (VAQA-Net, VTag-Net, VGQA-Net) that align with human judgments for video aesthetics and generation quality.
-
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
-
Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing
RC-GRPO-Editing constrains GRPO exploration to editing regions via localized noise and attention rewards, improving instruction adherence and non-target preservation in flow-based image editing.
-
ELT: Elastic Looped Transformers for Visual Generation
Elastic Looped Transformers share weights across recurrent blocks and apply intra-loop self-distillation to deliver 4x parameter reduction while matching competitive FID and FVD scores on ImageNet and UCF-101.
-
Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training
Data Warmup accelerates diffusion training on ImageNet by scheduling images from low to high complexity via a foreground-based metric and temperature-controlled sampler, improving FID and IS scores faster than uniform sampling.
-
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
VASR separates continuation and residual variance in reward-guided diffusion SMC, using optimal mass allocation and systematic resampling to achieve up to 26% better FID scores and faster runtimes than prior SMC and MCTS methods.
-
Towards Robust Content Watermarking Against Removal and Forgery Attacks
ISTS watermarking dynamically controls injection based on prompt semantics and uses two-sided detection to resist removal and forgery attacks in diffusion models.
-
Diffusion-Based Point-Cloud Generation of Heavy-Ion Events
A two-stage score-driven diffusion model with Point-Edge Transformer generates realistic high-multiplicity heavy-ion events as point clouds.
-
Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space
FOT-CFM generates turbulent fields in function space with superior high-order statistics and energy spectra on Navier-Stokes, Kolmogorov flow, and Hasegawa-Wakatani equations compared to baselines.
-
MC-GenRef: Annotation-free mammography microcalcification segmentation with generative posterior refinement
MC-GenRef performs annotation-free microcalcification segmentation via synthetic data from a lightweight image formation model plus test-time generative posterior refinement with a rectified-flow generator, yielding top Dice on INbreast and gains on an external cohort.
-
ML-based approach to classification and generation of structured light propagation in turbulent media
ML models classify and generate structured light in turbulence using CNNs and diffusion models enhanced by Bregman distance minimization.
-
NavCrafter: Exploring 3D Scenes from a Single Image
NavCrafter generates controllable novel-view videos from one image via video diffusion, geometry-aware expansion, and enhanced 3D Gaussian Splatting to achieve state-of-the-art synthesis under large viewpoint changes.
-
FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes
FluidFlow uses conditional flow-matching with U-Net and DiT architectures to predict pressure and friction coefficients on airfoils and 3D aircraft meshes, outperforming MLP baselines with better generalization.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
-
Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
Premier learns user-specific embeddings to modulate text-to-image generation, outperforming prior methods on preference alignment, text consistency, and expert ratings even with limited history.
-
Teaching an Agent to Sketch One Part at a Time
A multi-modal LM agent is trained to produce vector sketches part-by-part via supervised fine-tuning and process-reward RL on the new ControlSketch-Part dataset with automatic part annotations.
-
Conditional flow matching for physics-constrained inverse problems with finite training data
Conditional flow matching learns a velocity field to sample from measurement-conditioned posteriors in physics inverse problems, with early stopping to prevent variance collapse and selective memorization under finite training data.
-
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.
-
Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
SCFlowFR uses data-dependent coupling and shortcut constraints in flow matching to achieve state-of-the-art one-step face restoration with improved perceptual quality and efficiency.
-
MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
MaskDiME uses adaptive masked diffusion to produce 30x faster, localized, and semantically consistent visual counterfactual explanations without training, matching or exceeding prior performance on five datasets.
-
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.
-
Generative deep learning improves reconstruction of global historical climate records
A probabilistic generative deep learning framework reconstructs global historical climate fields from 1850 onward, revealing higher early 20th-century warming driven by stronger polar trends and localized modern hotspots compared to existing products.
-
Physics and causally constrained discrete-time neural models of turbulent dynamical systems
A framework builds stable neural models of turbulent dynamics by enforcing energy-preserving nonlinearities and causal constraints in discrete-time flow maps, demonstrated on Charney-DeVore and Lorenz-96 systems.
-
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
CMAD formulates compositional generation as cooperative stochastic optimal control among pre-trained diffusion models, validated on conditional MNIST against a gradient-guidance baseline.
-
Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
Under a Gaussian prior assumption, zero-shot diffusion posterior samplers for inverse problems admit closed-form spectral representations that enable a new parameter-selection framework balancing perceptual quality and signal fidelity.
-
Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
EmbedOpt optimizes the conditional embedding of protein diffusion models at inference time to shift the structural prior toward experimental constraints, outperforming coordinate-based posterior sampling on cryo-EM fitting while remaining robust across hyperparameter ranges.
-
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
An ELBO-based likelihood estimator from the final generated sample dominates other RL design factors for diffusion models, raising GenEval from 0.24 to 0.95 in 90 GPU hours with better efficiency than prior methods.
-
Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solvers
Diffusion inverse solvers are assessed for posterior fidelity using a new score-based Kernel Stein Discrepancy metric that requires no ground-truth posterior, revealing that reconstruction accuracy alone is insufficient.
-
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
ALGD augments the Lagrangian to locally convexify the energy landscape in diffusion models, stabilizing safe RL training and generation without changing optimal policies.
-
Sampling-Free Diffusion Transformers for Low-Complexity MIMO Channel Estimation
A diffusion transformer directly maps noisy MIMO channel observations to clean estimates in a single pass by exploiting angular sparsity, achieving better accuracy and much lower complexity than iterative diffusion baselines.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
-
Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.
-
Saving Foundation Flow-Matching Priors for Inverse Problems
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
-
Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection
Cross-matrix Krylov projection reuses shared subspaces from seed matrices to accelerate score pre-computation in diffusion models, delivering 15.8-43.7% time savings and up to 115x speedup versus DDPM baselines.
-
Forecasting implied volatility surface with generative diffusion models
A conditioned diffusion model with SNR-weighted arbitrage penalty generates one-day-ahead arbitrage-free implied volatility surfaces and outperforms baselines on market data.
-
Discrete Bayesian Sample Inference for Graph Generation
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.
-
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
-
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
UniWorld-V2 applies policy optimization via DiffusionNFT and MLLM logit feedback with group filtering to reach state-of-the-art scores of 4.49 on ImgEdit and 7.83 on GEdit-Bench while remaining model-agnostic.
-
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
-
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.
-
EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
EnScale emulates high-resolution regional climate model outputs from global circulation models for multiple variables using a two-step generative process with sparse local stochastic layers and energy score optimization, including a temporally consistent variant.
-
ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
ReNF proposes Boosted Direct Output (BDO) and parameter smoothing so a basic temporal MLP outperforms complex state-of-the-art models on long-term time series forecasting benchmarks by implicitly combining forecasts to reduce uncertainty.
-
Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT
CDPIR integrates cross-distribution diffusion priors from a Scalable Interpolant Transformer trained with classifier-free guidance into model-based iterative reconstruction to improve sparse-view CT under out-of-distribution conditions.
-
Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature
A physics-constrained consistency model downscales Greenland SMB and surface temperature by a factor of 32 while preserving coarse-scale sums and outperforming interpolation on test metrics.
-
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.