Density estimation using Real NVP
2016/05/27 by Laurent Dinh, Jascha Sohl‐Dickstein, Jascha Sohl-Dickstein +4 · 401 citations
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #Neural and Evolutionary Computing (cs.NE) #cs.AI #cs.LG #cs.NE #stat.ML
paper · pdf · doi:10.48550/arxiv.1605.08803
10 pages of main content, 3 pages of bibliography, 18 pages of appendix. Accepted at ICLR 2017
openalex publication_date 2016/05/27 · openalex created_date 2016/06/24 · arxiv created 2017/02/27 · arxiv updated 2017/03/01 · openalex updated_date 2026/07/31
Abstract
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation and latent variable manipulations.
Citations
Cited by
- Joint Flow Matching for Generator-Consistent Classification
- Normalizing Trajectory Models
- Normalizing Flows to Reconstruct Pseudo-PDFs
- Latent Confounded Causal Discovery via Lie Bracket Geometry
- Tilt Matching for Scalable Sampling and Fine-Tuning
- Improving Matrix Exponential for Generative AI Flows: A Taylor-Based Approach Beyond Paterson--Stockmeyer
- Variational Autoregressive Networks Applied to ϕ4 Field Theory Systems
- BabyFlow: 3D modeling of realistic and expressive infant faces
- The Ensemble Schrödinger Bridge filter for Nonlinear Data Assimilation
- An adaptive adjoint-oriented neural network for solving parametric optimal control problems with singularities
- Generative Modeling through Koopman Spectral Analysis: An Operator-Theoretic Perspective
- Estimating Solvation Free Energies with Boltzmann Generators
- Adapting Speech Language Model to Singing Voice Synthesis
- Improving the Accuracy of Amortized Model Comparison with Self-Consistency
- Transport Reversible Jump Markov Chain Monte Carlo with proposals generated by Variational Inference with Normalizing Flows
- StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis
- Computing quantum entanglement with machine learning
- Bidirectional Normalizing Flow: From Data to Noise and Back
- FALCON: Few-step Accurate Likelihoods for Continuous Flows
- Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
- Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank
- NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
- Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows
- SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
- Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization
- PAC-Bayesian Optimal Control with Stability and Generalization Guarantees
- Adversarial Jamming for Autoencoder Distribution Matching
- A Discrete Neural Operator with Adaptive Sampling for Surrogate Modeling of Parametric Transient Darcy Flows in Porous Media
- 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
- Spatiotemporal Pyramid Flow Matching for Climate Emulation
- Mapping of Lesion Images to Somatic Mutations
- Bayesian inference on Calabi--Yau moduli spaces and the axiverse: experimental data meets string theory
- Normalizing Flows on Quotient Manifolds via Boundary Quotients
- TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE
- Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
- Generative models for crystalline materials
- Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
- STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
- CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
- Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks
- Transformer Injectivity & Geometric Robustness - Analytic Margins and Bi-Lipschitz Uniformity of Sequence-Level Hidden States
- From Images to Physics: Probabilistic Inference of Galaxy Parameters and Emission Lines via VAE & Normalizing Flows
- FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
- Adaptive Symmetrization of the KL Divergence
- Learning to Validate Generative Models: a Goodness-of-Fit Approach
- Improving Conditional VAE with approximation using Normalizing Flows
- Detecting Generated Images by Fitting Natural Image Distributions
- DiScoFormer: Plug-In Density and Score Estimation with Transformers
- The Causal Round Trip: Generating Authentic Counterfactuals by Eliminating Information Loss
- Towards Causal Market Simulators
- A unified physics-informed generative operator framework for general inverse problems
- Reducing normalizing flow complexity for MCMC preconditioning
- Improving Bayesian inference in PTA data analysis: importance nested sampling with Normalizing Flows
- RefTon: Reference person shot assist virtual Try-on
- Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
- How Regularization Terms Make Invertible Neural Networks Bayesian Point Estimators
- Generative sampling with physics-informed kernels
- Group-Equivariant Diffusion Models for Lattice Field Theory
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
- CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
- FloDR: An invertible dimensionality reduction method based on a normalising flow
- Amortized Moment Matching for Visual Generation
- Learning Backward Transport for Source Localization
- The Score Hamiltonian: Mapping Diffusion Models to Adiabatic Transport
- Autoregressive Boltzmann Generators
- Generative Modeling via Drifting
- The Neural Differential Manifold: An Architecture with Explicit Geometric Structure
- Uniform Discrete Diffusion with Metric Path for Video Generation
- Bridging Simulators with Conditional Optimal Transport
- A Comprehensive Evaluation Framework for Synthetic Trip Data Generation in Public Transport
- Debiasing Reward Models by Representation Learning with Guarantees
- FARMER: Flow AutoRegressive Transformer over Pixels
- Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
- Variational Polya Tree
- MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
- Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
- HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
- On the flow matching interpretability
- Fisher meets Feynman: score-based variational inference with a product of experts
- Capability of using the normalizing flows for extraction rare gamma events in the TAIGA experiment
- GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models
- Learning Boltzmann Generators via Constrained Mass Transport
- Accelerating Bayesian Inference via Multi-Fidelity Transport Map Coupling
- Estimating Orbital Parameters of Direct Imaging Exoplanet Using Neural Network
- Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation
- Particle Dynamics for Latent-Variable Energy-Based Models
- Galaxy Morphology Classification with Counterfactual Explanation
- A DeepLagrangian method for learning and generating aggregation patterns in multi-dimensional Keller-Segel chemotaxis systems
- Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD
- Diffusion Transformers with Representation Autoencoders
- Adaptive Heterogeneous Mixtures of Normalising Flows for Robust Variational Inference
- Learning Regularization Functionals for Inverse Problems: A Comparative Study
- FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
- Conditional Flow Matching for Bayesian Posterior Inference
- On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification
- Rotated Mean-Field Variational Inference and Iterative Gaussianization
- Who Said Neural Networks Aren't Linear?
- metabeta -- A fast neural model for Bayesian mixed-effects regression
- Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi4 field theory
- HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
- Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows
- Neural Bayesian Filtering
- Learning Energy-based Variational Latent Prior for VAEs
- Marginal Girsanov Reweighting: Stable Variance Reduction for Long-Timescale Dynamics from Biased Simulation
- Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
- ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning
- Neural Canonical Transformation for the Spectra of Fluxional Molecule CH5+
- StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer
- CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
- Impute-MACFM: Imputation based on Mask-Aware Flow Matching
- Likelihood-free inference for gravitational-wave data analysis and public alerts
- Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
- Reversible GNS for Dissipative Fluids with Consistent Bidirectional Dynamics
- Exploring the Early Universe with Deep Learning
- Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy
- Random Projection Flows for Efficient Manifold Density Estimation
- Latent Iterative Refinement Flow: A Geometric-Constrained Approach for Few-Shot Generation
- TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
- Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
- FlowCrypt: Flow-Based Lightweight Encryption with Near-Lossless Recovery for Cloud Photo Privacy
- DINVMark: A Deep Invertible Network for Video Watermarking
- GEM-T: Generative Tabular Data via Fitting Moments
- Flow-Induced Diagonal Gaussian Processes
- Learning Neural Pushforward Samplers for Distributions from Fokker-Planck Equations by Weak Adversarial Training
- Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
- Fast reconstruction of degenerate populations of conductance-based neuron models from spike times
- 4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
- Causal Discovery via Quantile Partial Effect
- Learning to Generate Pointing Gestures in Situated Embodied Conversational Agents
- TabResFlow: A Normalizing Spline Flow Model for Probabilistic Univariate Tabular Regression
- Design-GenNO: A Physics-Informed Generative Model with Neural Operators for Inverse Microstructure Design
- NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
- VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
- LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models
- Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix
- Joint modeling of low and high extremes using a multivariate extended generalized Pareto distribution
- Divergence-kernel method for linear responses of densities and generative models
- An invertible generative model for forward and inverse problems
- BIDO: An Out-Of-Distribution Resistant Image-based Malware Detector
- Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling
- The distribution of calibrated likelihood functions on the probability-likelihood Aitchison simplex
- Generative AI for Crystal Structures: A Review
- Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals
- Improving the Accuracy of Amortized Model Comparison with Self-Consistency
- Search for Beyond the Standard Model physics with anomaly detection in multilepton final states in pp collisions at √(s)=13 TeV with the ATLAS detector
- Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy
- On Surjectivity of Neural Networks: Can you elicit any behavior from your model?
- Amortized Sampling with Transferable Normalizing Flows
- Efficient Identification of Critical Transitions via Flow Matching: A Scalable Generative Approach for Many-Body Systems
- DiffIER: Optimizing Diffusion Models with Iterative Error Reduction
- From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective
- Observable Optimization for Precision Theory: Machine Learning Energy Correlators
- MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
- Reverse Convolution and Its Applications to Image Restoration
- CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
- Learning Robust Satellite Attitude Dynamics with Physics-Informed Normalising Flow
- How and Why: Taming Flow Matching for Unsupervised Anomaly Detection and Localization
- CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series
- Probabilistic Emissivity Retrieval from Hyperspectral Data via Physics-Guided Variational Inference
- RadProPoser: A Framework for Human Pose Estimation with Uncertainty Quantification from Raw Radar Data
- SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
- Actionable Counterfactual Explanations Using Bayesian Networks and Path Planning with Applications to Environmental Quality Improvement
- Diffusion models for inverse problems
- Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
- DELTAv2: Accelerating Dense 3D Tracking
- Conformal C2ST: Turning weak classifiers into strong two-sample tests
- PIF-Net: Ill-Posed Prior Guided Multispectral and Hyperspectral Image Fusion via Invertible Mamba and Fusion-Aware LoRA
- Trans‐Conceptual Sampling: Bayesian Inference With Competing Assumptions
- Learning Neural Vocoder from Range-Null Space Decomposition
- Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation
- Joint Inference of Trajectory and Obstacle in Mean-Field Games via Bilevel Optimization
- Flow Stochastic Segmentation Networks
- A Comprehensive Review of Diffusion Models in Smart Agriculture: Progress, Applications, and Challenges
- Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks
- VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval
- Flow Matching Meets Biology and Life Science: A Survey
- Sparse-View 3D Reconstruction: Recent Advances and Open Challenges
- Controllable Video Generation: A Survey
- Neural Human Pose Prior
- Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans
- Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysis
- Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
- VAE-KRnet and its applications to variational Bayes
- Generative Latent Kernel Modeling for Blind Motion Deblurring
- Estimating Marginal Likelihoods in Likelihood-Free Inference via Neural Density Estimation
- Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation
- Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer
- Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning
- UniOD: A Universal Model for Outlier Detection across Diverse Domains
- Scaling can lead to compositional generalization
- Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems
- Deep Normalization for Speaker Vectors
- Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data
- Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data
- Generative flow-based warm start of the variational quantum eigensolver
- Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs
- Out-of-Distribution Detection Methods Answer the Wrong Questions
- Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
- Invertible Attention
- A Method to Model Conditional Distributions with Normalizing Flows
- Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
- D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
- Unfolding Generative Flows with Koopman Operators: Fast and Interpretable Sampling
- Quinoa: a Q-function You Infer Normalized Over Actions
- PrefPaint: Enhancing Image Inpainting through Expert Human Feedback
- Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
- Distilling Normalizing Flows
- On Convolutions, Intrinsic Dimension, and Diffusion Models
- Direct reconstruction of the Reionization history from 21cm 2D Power Spectra
- How to Train Your Energy-Based Models
- HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
- Style Transfer: A Decade Survey
- Operator Forces For Coarse-Grained Molecular Dynamics
- Exchangeable Neural ODE for Set Modeling
- Symmetric Wasserstein Autoencoders
- Multi-Target Emotional Voice Conversion With Neural Vocoders
- Flow-based Kernel Prior with Application to Blind Super-Resolution
- Deep generative models as the probability transformation functions
- Decoupling Global and Local Representations via Invertible Generative Flows
- Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
- MoiréXNet: Adaptive Multi-Scale Demoiréing with Linear Attention Test-Time Training and Truncated Flow Matching Prior
- Steering Your Diffusion Policy with Latent Space Reinforcement Learning
- Causal Autoregressive Flows
- A Variational Framework for Improving Naturalness in Generative Spoken Language Models
- Variational Inference with Mixtures of Isotropic Gaussians
- LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
- MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
- Scaling Probabilistic Circuits via Monarch Matrices
- Optimal Transport Driven Asymmetric Image-to-Image Translation for Nuclei Segmentation of Histological Images
- Learning to Integrate
- Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching
- On the performance of multi-fidelity and reduced-dimensional neural emulators for inference of physiological boundary conditions
- Learning Non-linear Wavelet Transformation via Normalizing Flow
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
- Natural Image Manipulation for Autoregressive Models Using Fisher Scores
- Neural Manifold Ordinary Differential Equations
- A purely Quantum Generative Modeling through Unitary Scrambling and Collapse
- Generalized Energy Based Models
- VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
- Flow-based Generative Models for Learning Manifold to Manifold Mappings
- Perceptual Image Restoration with High-Quality Priori and Degradation Learning
- STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
- Introduction to Normalizing Flows for Lattice Field Theory
- Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data
- Approximating exponential family models (not single distributions) with a two-network architecture
- Learning normalized image densities via dual score matching
- Aligning Latent Spaces with Flow Priors
- Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence
- Winner-takes-all for Multivariate Probabilistic Time Series Forecasting
- Compression with Flows via Local Bits-Back Coding
- Metropolis-Hastings Generative Adversarial Networks
- Set Flow: A Permutation Invariant Normalizing Flow
- Wasserstein Dependency Measure for Representation Learning
- Semi-Supervised Learning with Normalizing Flows
- Equivariant Hamiltonian Flows
- Learning to Shift Attention for Motion Generation
- Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
- Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: Application to parameter estimation
- Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
- Revisiting Unbiased Implicit Variational Inference
- Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
- Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
- ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration
- Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning
- Adversarial Causal Tuning for Realistic Time-series Generation
- Asymptotically exact variational flows via involutive MCMC kernels
- Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
- Flexible Selective Inference with Flow-based Transport Maps
- Base-Detail Feature Learning Framework for Visible-Infrared Person Re-Identification
- Neural Path Guiding with Distribution Factorization
- Learning to Learn to Compress
- Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding
- Learning Geometry and Topology via Multi-Chart Flows
- BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models
- Model-Informed Flows for Bayesian Inference
- Inductive Representation Learning on Temporal Graphs
- Generative modelling of multivariate geometric extremes using normalising flows
- Normalizing Flows are Capable Models for Continuous Control
- Variational Determinant Estimation with Spherical Normalizing Flows
- Relative gradient optimization of the Jacobian term in unsupervised deep learning
- DiCoFlex: Model-agnostic diverse counterfactuals with flexible control
- JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows
- FloWaveNet : A Generative Flow for Raw Audio
- Symplectic Generative Networks (SGNs): A Hamiltonian Framework for Invertible Deep Generative Modeling
- Mitigating Generation Shifts for Generalized Zero-Shot Learning
- Deep Variational Inference Without Pixel-Wise Reconstruction
- Bilateral Denoising Diffusion Models
- Probabilistic Software Modeling: A Data-driven Paradigm for Software Analysis
- Wavelet Flow For Extragalactic Foreground Simulations
- Can Transformers help us perform parameter estimation of overlapping signals in gravitational wave detectors?
- Computer Vision and Normalizing Flow-Based Defect Detection
- Self Normalizing Flows
- Generalizing Hamiltonian Monte Carlo with Neural Networks
- Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage
- GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
- Gradients as Features for Deep Representation Learning
- EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
- Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems
- Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
- Guided Image Generation with Conditional Invertible Neural Networks
- Invertible Denoising Network: A Light Solution for Real Noise Removal
- From Image to Imuge: Immunized Image Generation
- Multivariate Latent Recalibration for Conditional Normalizing Flows
- Copula-like Variational Inference
- Generative models for sampling of lattice field theories
- Surfing: Iterative optimization over incrementally trained deep networks
- Using a thousand optimization tasks to learn hyperparameter search strategies
- Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows
- MeshODE: A Robust and Scalable Framework for Mesh Deformation
- Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry
- Generative Adversarial Learning via Kernel Density Discrimination
- Hybrid Bernstein Normalizing Flows for Flexible Multivariate Density Regression with Interpretable Marginals
- Black-Box Inference for Non-Linear Latent Force Models
- Accelerate TarFlow Sampling with GS-Jacobi Iteration
- Multi-View Wireless Sensing via Conditional Generative Learning: Framework and Model Design
- Trustworthy Image Super-Resolution via Generative Pseudoinverse
- ReBRAC-v2: The Return of the King
- A Compact Network Learning Model for Distribution Regression
- Geometrically Enriched Latent Spaces
- BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images
- GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
- Recent Advances in Diffusion Models for Hyperspectral Image Processing and Analysis: A Review
- Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
- Autoregressive Score Matching
- Inverse Learning of Symmetries
- Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
- Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
- Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference
- Semantic and Geometric Unfolding of StyleGAN Latent Space
- Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
- Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry
- MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
- You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts
- Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility
- Adaptive Kernel Density Estimation with Pre-training
- Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation
- Neural Entropic Estimation: A faster path to mutual information estimation
- Boosting Statistic Learning with Synthetic Data from Pretrained Large Models
- Large Causal Models for Temporal Causal Discovery
- Enhancing Obsolescence Forecasting with Deep Generative Data Augmentation: A Semi-Supervised Framework for Low-Data Industrial Applications
- Globally Injective ReLU Networks
- Detecting Modeling Bias with Continuous Time Flow Models on Weak Lensing Maps
- Understanding the (un)interpretability of natural image distributions using generative models
- Dynamical Partition Functions of Stochastic Dynamics via Variational Flows
- BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Python
- Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations
- Modeling the Gaia Color-Magnitude Diagram with Bayesian Neural Flows to Constrain Distance Estimates
- Neural Discriminant Analysis for Deep Speaker Embedding
- Using Variational Inference to Improve the Efficiency of MCMC Algorithms
- The Invisible Gorilla Effect in Out-of-distribution Detection
- Contrastive Embedding for Generalized Zero-Shot Learning
- MIM: Mutual Information Machine
- PixelCNN Models with Auxiliary Variables for Natural Image Modeling
- NVAE: A Deep Hierarchical Variational Autoencoder
- X2CT-FLOW: Maximum a posteriori reconstruction using a progressive flow-based deep generative model for ultra sparse-view computed tomography in ultra low-dose protocols
- Latent Reasoning with Normalizing Flows
- Visual Attention in Imaginative Agents
- Self-Aware Object Detection via Degradation Manifolds
- InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
- When Does LeJEPA Learn a World Model?
- Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design
- Energy-Based Coarse-Graining in Molecular Dynamics: A Flow-Based Framework without Data
- Estimating Density Functions for Probabilistic Power Flow Using Invertible Neural Networks
- Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
- From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources
- Learning Brenier Potentials with Convex Generative Adversarial Neural Networks
- SD-KDE: Score-Debiased Kernel Density Estimation
- HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models
- Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning
- When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction
- Three-Body Earth-Moon Transfers with Different Departure/Arrival Orbital Altitudes: New Phenomenon and Diffusion Model-Augmented Construction
- Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
- MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark
- Parallel Multiscale Autoregressive Density Estimation
- Out-of-Distribution Detection of Melanoma using Normalizing Flows
- Latent Bayesian Optimization via Autoregressive Normalizing Flows
- MDCA-Net: a multi-directional alignment and dynamic context aggregation network for optical and SAR image fusion
- Data-driven Regularization via Racecar Training for Generalizing Neural Networks
- A novel stellar spectrum denoising method based on deep Bayesian modeling
- Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
- Metropolis-Hastings view on variational inference and adversarial training
- Secure Data Sharing With Flow Model
- Improving Sequential Latent Variable Models with Autoregressive Flows
- RBM-Flow and D-Flow: Invertible Flows with Discrete Energy Base Spaces
- Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
- Arbitrary Conditional Distributions with Energy
- Fully probabilistic quasar continua predictions near Lyman-α with conditional neural spline flows
- Variational Bayes: A report on approaches and applications
- A Bidirectional DeepParticle Method for Efficiently Solving Low-dimensional Transport Map Problems
- Hierarchical Flow Matching for 3D Point Cloud Generation
- Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations
- A real-time anomaly detection method for robots based on a flexible and sparse latent space
- Robust Bayesian methods using amortized simulation-based inference
- Improving the evaluation of samplers on multi-modal targets
- Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging
- Generative Artificial Intelligence for Internet of Things Computing: A Systematic Survey
- Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
- Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection
- Gaussian Process Tilted Nonparametric Density Estimation using Fisher Divergence Score Matching
- RoSMM: A Robust and Secure Multi-Modal Watermarking Framework for Diffusion Models
Related