Imagen de Portada

How well do generative models solve inverse problems? A benchmark study

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Krüger, Patrick, Materne, Patrick, Krebs, Werner, Gottschalk, Hanno
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generative Inverse Design with Abstention via Diagonal Flow Matching
por: de Campos, Miguel, et al.
Publicado: (2026)

Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
por: Krüger, Patrick, et al.
Publicado: (2026)

Generative Design of Ship Propellers using Conditional Flow Matching
por: Kruger, Patrick, et al.
Publicado: (2026)

An invertible generative model for forward and inverse problems
por: van Leeuwen, Tristan, et al.
Publicado: (2025)

Conditional score-based diffusion models for solving inverse problems in mechanics
por: Dasgupta, Agnimitra, et al.
Publicado: (2024)

RED-DiffEq: Regularization by denoising diffusion models for solving inverse PDE problems with application to full waveform inversion
por: Shan, Siming, et al.
Publicado: (2025)

Weak neural variational inference for solving Bayesian inverse problems without forward models: applications in elastography
por: Scholz, Vincent C., et al.
Publicado: (2024)

Scalable physics-informed deep generative model for solving forward and inverse stochastic differential equations
por: Zhou, Shaoqian, et al.
Publicado: (2025)

Physics-informed neural networks to solve inverse problems in unbounded domains
por: Pérez-Bernal, Gregorio, et al.
Publicado: (2025)

Regularity of Solutions to Beckmann's Parametric Optimal Transport
por: Gottschalk, Hanno, et al.
Publicado: (2026)

How predictable is language model benchmark performance?
por: Owen, David
Publicado: (2024)

Diffusion models for inverse problems
por: Chung, Hyungjin, et al.
Publicado: (2025)

Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
por: Nelsen, Nicholas H., et al.
Publicado: (2025)

A unified physics-informed generative operator framework for general inverse problems
por: Bao, Gang, et al.
Publicado: (2025)

VideoGAN-based Trajectory Proposal for Automated Vehicles
por: Mariani, Annajoyce, et al.
Publicado: (2025)

FlamePINN-1D: Physics-informed neural networks to solve forward and inverse problems of 1D laminar flames
por: Wu, Jiahao, et al.
Publicado: (2024)

Tabular foundation model for GEOAI benchmark problems BM/AirportSoilProperties/2/2025
por: Saito, Taiga, et al.
Publicado: (2025)

Quality-factor inspired deep neural network solver for solving inverse scattering problems
por: Du, Yutong, et al.
Publicado: (2025)

MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification
por: Fieback, Laura, et al.
Publicado: (2024)

Hyperparameter Optimization for Driving Strategies Based on Reinforcement Learning
por: Adde, Nihal Acharya, et al.
Publicado: (2024)

Geophysical inverse problems with measurement-guided diffusion models
por: Ravasi, Matteo
Publicado: (2025)

Learning to solve Bayesian inverse problems: An amortized variational inference approach using Gaussian and Flow guides
por: Karumuri, Sharmila, et al.
Publicado: (2023)

Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
por: Maag, Kira, et al.
Publicado: (2019)

A method for quantifying the generalization capabilities of generative models for solving Ising models
por: Ma, Qunlong, et al.
Publicado: (2024)

Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
por: Riedlinger, Tobias J., et al.
Publicado: (2025)

Anchor function: a type of benchmark functions for studying language models
por: Zhang, Zhongwang, et al.
Publicado: (2024)

MotifBench: A standardized protein design benchmark for motif-scaffolding problems
por: Zheng, Zhuoqi, et al.
Publicado: (2025)

A Gibbs posterior sampler for inverse problem based on prior diffusion model
por: Giovannelli, Jean-François
Publicado: (2026)

Generative Adversarial Learning from Deterministic Processes
por: Kühl, Joris C., et al.
Publicado: (2026)

How many measurements are enough? Bayesian recovery in inverse problems with general distributions
por: Adcock, Ben, et al.
Publicado: (2025)

Call for Action: towards the next generation of symbolic regression benchmark
por: Aldeia, Guilherme S. Imai, et al.
Publicado: (2025)

Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
por: Wang, Yizheng, et al.
Publicado: (2024)

HomPINNs: homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions
por: Zheng, Haoyang, et al.
Publicado: (2023)

A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
por: Fontanesi, Michele, et al.
Publicado: (2025)

Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
por: Adde, Nihal Acharya, et al.
Publicado: (2025)

Hybrid safe-strong rules for efficient optimization in lasso-type problems
por: Zeng, Yaohui, et al.
Publicado: (2017)

HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative models
por: Meng, Tingwei, et al.
Publicado: (2024)

GraphBench: Next-generation graph learning benchmarking
por: Stoll, Timo, et al.
Publicado: (2025)

Mathematics of statistical sequential decision-making: concentration, risk-awareness and modelling in stochastic bandits, with applications to bariatric surgery
por: Saux, Patrick
Publicado: (2024)

When do World Models Successfully Learn Dynamical Systems?
por: Ross, Edmund, et al.
Publicado: (2025)