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.
hub
Generative Modeling by Estimating Gradients of the Data Distribution
27 Pith papers cite this work. Polarity classification is still indexing.
27
Pith papers citing it
abstract
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as the sampling process gets closer to the data manifold. Our framework allows flexible model architectures, requires no sampling during training or the use of adversarial methods, and provides a learning objective that can be used for principled model comparisons. Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.
hub tools
citation-role summary
background 2
baseline 1
method 1
citation-polarity summary
representative citing papers
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.
SBTG recovers the Jacobian of the nonlinear transition map between brain states by multiplying cross-block scores from denoising models, enabling inference of lag-specific directed interactions in neural population data such as C. elegans calcium imaging.
A score-based diffusion generative model on deep infrared galaxy photometry yields a star formation rate density peaking at z=1.3 and shows distinct non-parametric star formation histories plus AGN activity peaking during the quenching transition of massive galaxies.
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
A plug-and-play differentiable model bridging ray and wave optics for hybrid systems that enables end-to-end optimization of planar and conformal diffractive elements.
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
Implicit score matching trains diffusion models that successfully sample SU(3) Wilson gauge configurations on lattices, with a Hamiltonian-dynamics corrector needed for strong coupling.
A unified framework for exponential tilting in diffusion and flow models that includes bias-variance decompositions showing finite gradient variance for some methods, norm bounds on adjoint ODEs, and adapted losses with new Crooks and Jarzynski identities.
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.
Adjoint matching objectives derived from the Stochastic Maximum Principle have critical points satisfying HJB stationarity conditions for SOC problems with control-dependent drift and diffusion.
MIOFlow 2.0 learns stochastic cellular trajectories from transcriptomics data via neural SDEs, unbalanced optimal transport for growth, and a joint latent space unifying gene expression with spatial features.
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.
A unified probabilistic model uses per-atom logits over crystal prototypes to denoise atomic configurations, classify phases, and derive order parameters from a single differentiable scalar field.
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.
Score-based diffusion models learn the empirical distribution of real LIGO noise to enable unbiased gravitational-wave parameter estimation under only an additivity assumption.
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
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.
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
Diffusion models are reorganized under a Langevin perspective that unifies ODE and SDE formulations and shows flow matching is equivalent to denoising under maximum likelihood.
Applies diffusion models to generate 10,000 neutrino mass matrices consistent with oscillation parameters in a seesaw model, revealing non-trivial distributions in CP phases and 0νββ effective mass.
citing papers explorer
-
Generative models on phase space
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.
-
Denoising Diffusion Implicit Models
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.
-
Inferring Active Neural Circuits Using Diffusion Scores
SBTG recovers the Jacobian of the nonlinear transition map between brain states by multiplying cross-block scores from denoising models, enabling inference of lag-specific directed interactions in neural population data such as C. elegans calcium imaging.
-
pop-cosmos: Star formation over 12 Gyr from generative modelling of a deep infrared-selected galaxy catalogue
A score-based diffusion generative model on deep infrared galaxy photometry yields a star formation rate density peaking at z=1.3 and shows distinct non-parametric star formation histories plus AGN activity peaking during the quenching transition of massive galaxies.
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
A General Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization
A plug-and-play differentiable model bridging ray and wave optics for hybrid systems that enables end-to-end optimization of planar and conformal diffractive elements.
-
PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives
PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.
-
Diffusion model for SU(N) gauge theories
Implicit score matching trains diffusion models that successfully sample SU(3) Wilson gauge configurations on lattices, with a Hamiltonian-dynamics corrector needed for strong coupling.
-
A unified perspective on fine-tuning and sampling with diffusion and flow models
A unified framework for exponential tilting in diffusion and flow models that includes bias-variance decompositions showing finite gradient variance for some methods, norm bounds on adjoint ODEs, and adapted losses with new Crooks and Jarzynski identities.
-
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.
-
Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
Adjoint matching objectives derived from the Stochastic Maximum Principle have critical points satisfying HJB stationarity conditions for SOC problems with control-dependent drift and diffusion.
-
MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data
MIOFlow 2.0 learns stochastic cellular trajectories from transcriptomics data via neural SDEs, unbalanced optimal transport for growth, and a joint latent space unifying gene expression with spatial features.
-
Diffusion Models Memorize in Training -- and Generalize in Inference
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.
-
A probabilistic framework for crystal structure denoising, phase classification, and order parameters
A unified probabilistic model uses per-atom logits over crystal prototypes to denoise atomic configurations, classify phases, and derive order parameters from a single differentiable scalar field.
-
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.
-
Gravitational-Wave Parameter Estimation in non-Gaussian noise using Score-Based Likelihood Characterization
Score-based diffusion models learn the empirical distribution of real LIGO noise to enable unbiased gravitational-wave parameter estimation under only an additivity assumption.
-
Shap-E: Generating Conditional 3D Implicit Functions
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
-
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
-
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.
-
Scaling Properties of Continuous Diffusion Spoken Language Models
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
-
Rethinking the Diffusion Model from a Langevin Perspective
Diffusion models are reorganized under a Langevin perspective that unifies ODE and SDE formulations and shows flow matching is equivalent to denoising under maximum likelihood.
-
Exploring the flavor structure of leptons via diffusion models
Applies diffusion models to generate 10,000 neutrino mass matrices consistent with oscillation parameters in a seesaw model, revealing non-trivial distributions in CP phases and 0νββ effective mass.
-
Towards a Universal Foundation Model for Protein Dynamics: A Multi-Chain Tree-Structured Framework with Transformer Propagators
Proposes TSCG hierarchical representation and Transformer propagator for universal coarse-grained protein MD with claimed 10k-20k times acceleration over all-atom MD while preserving statistical properties.
-
A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios
A synthesis of diffusion-based simulation-based inference methods that address model misspecification, irregular observations, and missing data in scientific applications.
-
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.