{"total":13,"items":[{"citing_arxiv_id":"2606.10023","ref_index":114,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions","primary_cat":"astro-ph.CO","submitted_at":"2026-06-08T18:08:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25210","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning","primary_cat":"cs.LG","submitted_at":"2026-05-24T18:19:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21489","ref_index":75,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Variance Reduction for Expectations with Diffusion Teachers","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:59:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21094","ref_index":62,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems","primary_cat":"cs.LG","submitted_at":"2026-05-20T12:25:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twist condition.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08976","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations","primary_cat":"cs.CE","submitted_at":"2026-05-09T14:36:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and conditional tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"differences, respecting Neumann boundary conditions. I.1 Domain discretization After discretization, we decomposed the discretized domain D={0, . . . , d 1} × {0, . . . , d2} in the same spirit into its interior, left, top, right and bottom part: D◦ :={1, . . . , d 1 −2} × {1, . . . , d2 −2};(25) ∂LD:={0} × {0, . . . , d 2 −2);(26) ∂T D:={0, . . . , d 2 −2} × {d 2 −1};(27) ∂RD:={d 1 −1} × {1, . . . , d2 −1};(28) ∂BD:={1, . . . , d 1 −1} × {0}.(29) 19 SBGMTHROUGHANISOTROPICSPDES-PREPRINT- MAY12, 2026 I.2 Spatial discretization For the finite-difference approximation we have chosen, the discretized drift is given by ˜b(t, u)i :=   "},{"citing_arxiv_id":"2604.19736","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Generative Drifting for Conditional Medical Image Generation","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:58:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GDM reformulates 3D conditional medical image generation as attractive-repulsive drifting with multi-level feature banks to balance distribution plausibility, patient fidelity, and one-step inference, outperforming GANs, flows, and SDEs on MRI-to-CT and sparse CT tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11375","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DiLO: Decoupling Generative Priors and Neural Operators via Diffusion Latent Optimization for Inverse Problems","primary_cat":"math.NA","submitted_at":"2026-04-13T12:15:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DiLO turns diffusion sampling into deterministic latent optimization to satisfy the manifold consistency requirement for neural operators in inverse problem solving.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.20549","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sample-efficient evidence estimation of score based priors for model selection","primary_cat":"cs.LG","submitted_at":"2026-02-24T05:06:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DiME estimates model evidence for diffusion priors by integrating time-marginals from posterior sampling, enabling efficient prior selection and misfit diagnosis in ill-posed inverse problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.18654","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance","primary_cat":"cs.LG","submitted_at":"2025-07-22T19:35:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Piecewise guidance in diffusion posterior sampling cuts inference time 23-25% on inpainting and super-resolution with negligible PSNR/SSIM loss while handling measurement noise.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.18782","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Joint Reconstruction of Activity and Attenuation in PET by Diffusion Posterior Sampling in Wavelet Coefficient Space","primary_cat":"physics.med-ph","submitted_at":"2025-05-24T16:39:50+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.17353","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dual Ascent Diffusion for Inverse Problems","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:12:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.00083","ref_index":47,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Diffusion Models for Inverse Problems","primary_cat":"cs.LG","submitted_at":"2024-09-30T17:34:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tersection of diffusion models and inverse problems. 1 Introduction 1.1 Problem Setting Inverse problems are ubiquitous and the associated reconst ruction problems have tremendous appli- cations across different domains such as seismic imaging [3 7, 38], weather prediction [39], oceanog- raphy [40], audio signal processing [41, 42, 43, 44, 45, 46], medical imaging [47, 48, 49, 50], etc. Despite their generality, inverse problems across different domains follow a fairly unified mathemat- ical setting. Specifically, in inverse problems, the goal is to recover an unknown sample x∈ Rn from a distribution pX, assuming access to measurements y∈ Rm and a corruption model Y =A(X) + σyZ, Z∼N (0, I m). (1.1) In what follows, we present some well-known examples of meas urement models that fit under this"},{"citing_arxiv_id":"2312.15676","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation","primary_cat":"eess.IV","submitted_at":"2023-12-25T09:47:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"3DGR-CT adapts 3D Gaussian splatting with FBP-guided initialization and differentiable CT projection for sparse-view reconstruction, claiming better accuracy and speed than prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}