Overview

Inverse problems work backward from observations to estimate the hidden image, physical state, or system parameters that produced them, often when measurements are sparse, noisy, or ambiguous. Methods range from classical regularization and optimization to physics-informed neural networks, learned operators, and generative priors such as diffusion and flow models; Bayesian methods can also represent multiple plausible solutions and their uncertainty. Applications include medical and computational imaging, seismic exploration, spectroscopy, and identifying material or dynamical properties from sensor data. A central challenge is balancing measurement consistency with useful prior information: learned priors can recover detail but may invent unsupported structure, especially when the forward model or data differs from training, so identifiability, stability, and calibrated uncertainty remain important.

Latest papers

CardsList

266 papers22 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

  1. Physically Admissible Generative Flow Matching for Sparse Flow Reconstruction

    Nov 17, 2026Yuhao Wang, Yuanxi PengPhysics-Informed Generative ModelingConstrained Flow Matching

  2. ThermoSight: From Appearance to Internal Thermofluid Fields via Physics-Guided Neural Reconstruction

    Nov 16, 2026Yuhao Fang, Chenglin Lu, Hefei Ling +1Inverse ProblemsThermal Imaging

  3. CiGS: Conduction in Gaussian Splats for Interior Temperature Field from Thermal Images

    Nov 15, 2026Liu Zhenyuan, Bharath Seshadri, Bailey Miller +3Inverse ProblemsPDE Inverse Problems

  4. Electrocardiographic Imaging via Posterior Sampling under Operator Discrepancy

    Nov 13, 2026Ricarda Buttmann, Andreas M. LehrmannElectrocardiographyDiffusion Posterior Sampling

  5. A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning

    Nov 11, 2026Gen Li, Zhaoyun Zong, Diqiong Jiang +1Inverse ProblemsSeismic Imaging

  6. Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser

    Nov 10, 2026Dibyanshu Kumar, Magda GregorovaInverse ProblemsAlternating Direction Method of Multipliers

  7. AdjointFlow: Accelerating Scientific Inverse Problems with Physics-Based Transport

    Nov 10, 2026Ethan Hanold, Nicholas M. Boffi, Qin Li +1Inverse ProblemsPhysics-Informed Generative Modeling

  8. Formalizing inverse problems in the age of AI: possibilities, pitfalls, and an invitation

    Nov 4, 2026Christian Clason, Tapio Helin, Medet Nursultanov +1AutoformalizationFormal Verification

  9. FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems

    Nov 4, 2026Junseo Bang, Daewon Choi, Dong Ju Mun +1Flow-Based Generative ModelingInverse Problems

  10. DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning

    Nov 2, 2026Peng Jin, Yinan Feng, Yinpeng Chen +2Inverse ProblemsSelf-Supervised RL

  11. The Prior-Force Family of Implicit Denoiser Priors and Its Decisions in Linear Inverse Problems

    Oct 30, 2026Weijie Liang, Chuling Wen, Jian LuLinear Inverse ProblemsImplicit Regularization

  12. Retrieval-Augmented Initialization with Dual-Guided Inversion for Flow-Based Inverse Problem Solvers

    Oct 30, 2026Hansam Cho, Seoung Bum KimInverse ProblemsImage Inverse Problems

  13. FlowFPR: Flow Matching Prior for Oversampled Fourier Phase Retrieval

    Oct 30, 2026Li Jiatai, Cao Wenfei, Chen Yang +1Image Inverse ProblemsInverse Problems

  14. Multi-Solution Inverse Design of Pixelated Patch Antennas Using an Autoregressive Transformer

    Oct 29, 2026Young-Mok Yun, Seung-Won Shin, Jaeyong Chung +1Inverse DesignInverse Problems

  15. Inverse modelling of a laser-plasma accelerator

    Oct 27, 2026Mykyta Lenivenko, Arnaud Beck, Hayg Guler +9Inverse ProblemsParameter Estimation

  16. The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit

    Oct 26, 2026Amedeo Chiefa, Luigi Del Debbio, Richard KenwayNeural Network Training DynamicsNeural Tangent Kernel

  17. Sparse Reconstruction by Direct Measurement-to-Field Generation in Function Space

    Oct 26, 2026Linzheng Wang, Jason Chen, Nicolas Tricard +3Sparse RecoveryInverse Problems

  18. Beyond Best-of-kk: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems

    Oct 22, 2026Merve Kocabas, Benjamin A. Burns, Andreas Geiger +2Diffusion-Based Inverse ProblemsInverse Problems

  19. Compositional neural networks for multimodal X-ray and neutron scattering inversion

    Oct 21, 2026Valentin Munteanu, Alexander Hinderhofer, Dmitry Lapkin +2Inverse ProblemsUncertainty-Aware Multimodal Fusion

  20. Diffusion Posterior Sampling with Uncertain Forward Models

    Oct 21, 2026Wentao Shangguan, Vivek K GoyalDiffusion-Based Inverse ProblemsDiffusion Posterior Sampling

  21. PnP-CF: A Consensus Flow-Matching Solver for General Inverse Problems

    Oct 19, 2026Dibyanshu Kumar, Magda GregorovaInverse ProblemsFlow Matching

  22. Mixed Poisson diffusion models and application to posterior sampling

    Oct 14, 2026Thibaut Pellerin, Alain Durmus, Elinor Berger +1Diffusion ModelsDiffusion Posterior Sampling

  23. DiffGIPC: Differentiable Mixed-Coordinate Contact Mechanics on GPU

    Oct 13, 2026Kemeng Huang, Bowen Ren, Xinyu Lu +2Differentiable PhysicsInverse Problems

  24. Physical-Field-Bridged Material Parameter Inference from Multi-View Deformation Videos

    Oct 13, 2026Linrui Shou, Jie Li, Yu Liu +1Materials Property PredictionInverse Problems

  25. Taming Nonconvexity with Epigraph Lifting

    Oct 12, 2026Clara Lage, Hok Shing Wong, Matthias EhrhardtNonconvex OptimizationInverse Problems