{"total":27,"items":[{"citing_arxiv_id":"2605.23365","ref_index":24,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Score-Based One-step MeanFlow Policy Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:28:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SOM is an actor-critic algorithm that constructs the target velocity field for one-step MeanFlow policies directly from the Q-function via score estimation and probability flow ODE, achieving claimed SOTA on locomotion tasks with reduced training and inference time.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22765","ref_index":33,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation","primary_cat":"cs.LG","submitted_at":"2026-05-21T17:27:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Uniform diffusion models rely on a leave-one-out denoiser rather than the usual denoising posterior, with exact conversions derived; an absorbing-state reformulation is introduced that matches or exceeds masked diffusion on language modeling while preserving the original joint distribution.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21041","ref_index":6,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Conditioning Gaussian Processes on Almost Anything","primary_cat":"stat.ML","submitted_at":"2026-05-20T11:23:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Equivalence between Gaussian processes and linear diffusion models enables general conditioning on arbitrary pointwise likelihoods via ODE dynamics and Monte Carlo guidance approximation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19256","ref_index":25,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Distribution Matching Distillation without Fake Score Network","primary_cat":"cs.CV","submitted_at":"2026-05-19T02:05:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FSF-DMD replaces the fake-score network in distribution matching distillation with a generator-induced pseudo-velocity surrogate for flow-map generators, showing improved FID on ImageNet-1K 256x256.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19119","ref_index":60,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization","primary_cat":"cs.NE","submitted_at":"2026-05-18T21:11:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09654","ref_index":32,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Metropolis-Adjusted Diffusion Models","primary_cat":"stat.ML","submitted_at":"2026-05-10T16:57:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Metropolis-adjusted Langevin correctors using score-based acceptance probabilities, including an exact Bernoulli factory method and a Simpson's rule approximation, reduce sampling bias in diffusion models and improve FID scores.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09319","ref_index":36,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection","primary_cat":"cs.CV","submitted_at":"2026-05-10T04:32:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PGID restores watermark detection in diffusion models by using progressive inversion-denoising cycles to correct latents displaced by removal or forgery attacks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[34] Yang Song and Stefano Ermon. Generative modeling by estimating gradients of the data distribution. InAdvances in Neural Information Processing Systems, pages 11895-11907, 2019. [35] Yang Song, Conor Durkan, Iain Murray, and Stefano Ermon. Maximum likelihood training of score-based diffusion models. InThirty-Fifth Conference on Neural Information Processing Systems, 2021. [36] Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations, 2021. [37] Anubhav Jain, Yuya Kobayashi, Naoki Murata, Yuhta Takida, Takashi Shibuya, Yuki Mitsufuji, Niv Cohen, Nasir D."},{"citing_arxiv_id":"2605.08960","ref_index":10,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-09T13:56:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CrystalREPA closes the representation gap between crystal generators and universal MLIPs via contrastive alignment, yielding more stable and valid generated crystals while revealing that MLIP teacher quality is better predicted by representation distinguishability than by leaderboard accuracy.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and Saining Xie. Representation alignment for generation: Training diffusion transformers is easier than you think. InThe Thirteenth International Conference on Learning Representations, 2025. [9] Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840-6851, 2020. [10] Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations, 2021. [11] Youzhi Luo, Chengkai Liu, and Shuiwang Ji. Towards symmetry-aware generation of periodic materials.Advances in Neural Information Processing Systems, 36:53308-53329, 2023."},{"citing_arxiv_id":"2605.06376","ref_index":50,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Continuous-Time Distribution Matching for Few-Step Diffusion Distillation","primary_cat":"cs.CV","submitted_at":"2026-05-07T14:56:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"CDM migrates distribution matching distillation to continuous time via dynamic random-length schedules and active off-trajectory latent alignment, yielding competitive few-step image fidelity on SD3 and Longcat-Image.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06140","ref_index":2,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"SymDrift: One-Shot Generative Modeling under Symmetries","primary_cat":"cs.LG","submitted_at":"2026-05-07T12:38:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SymDrift makes drifting models produce symmetry-invariant samples in one step via symmetrized coordinate drifts or G-invariant embeddings, outperforming prior one-shot baselines on molecular benchmarks and cutting compute by up to 40x.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05606","ref_index":30,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows","primary_cat":"stat.ML","submitted_at":"2026-05-07T02:47:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A variational method learns a neural approximation to the conditional backward-in-time score of the posterior SDE, inducing an ELBO for joint smoothing and parameter learning from sparse data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23740","ref_index":26,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Transformer as an Euler Discretization of Score-based Variational Flow","primary_cat":"cs.LG","submitted_at":"2026-04-26T14:36:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The Transformer is recovered exactly as the forward Euler step of spherical SVFlow, with multi-head attention and MoE/FFN as approximations to its vector field.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16801","ref_index":109,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Continuous Limits of Coupled Flows in Representation Learning","primary_cat":"cs.LG","submitted_at":"2026-04-18T03:19:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[107] Justin Sirignano and Konstantinos Spiliopoulos. Mean field analysis of neural networks: A law of large numbers.SIAM Journal on Applied Mathematics, 80(2):725-752, 2020. [108] Samuel L Smith, Benoit Dherin, David GT Barrett, and Soham De. On the origin of im- plicit regularization in stochastic gradient descent. InInternational Conference on Learning Representations, 2021. [109] Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations, 2021. [110] Gilbert Strang.Introduction to Linear Algebra. Wellesley-Cambridge Press, Wellesley, MA, 1st edition, 1993."},{"citing_arxiv_id":"2604.11375","ref_index":12,"ref_count":1,"confidence":0.55,"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":"2510.01608","ref_index":51,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems","primary_cat":"cs.CV","submitted_at":"2025-10-02T02:45:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical performance across compressive sensing, deblurring, super-resolution, CT, and MRI.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.21912","ref_index":70,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching","primary_cat":"cs.LG","submitted_at":"2025-09-26T05:51:31+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.08390","ref_index":50,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","primary_cat":"cs.LG","submitted_at":"2025-07-11T08:00:47+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PG-DLM applies particle Gibbs sampling over full trajectories in diffusion language models to enable iterative refinement, yielding higher accuracy on reward-guided generation with theoretical convergence guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.00480","ref_index":52,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:55:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Reformulates constrained black-box optimization as posterior inference in latent space of flow-based models amortized by outsourced diffusion models, claiming superior performance on synthetic and real tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.13763","ref_index":47,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value","primary_cat":"cs.LG","submitted_at":"2025-06-16T17:59:54+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.00433","ref_index":57,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis","primary_cat":"cs.CV","submitted_at":"2025-05-31T07:28:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Latent Wavelet Diffusion uses wavelet energy map masking and a scale-consistent VAE to improve detail fidelity in 2K-4K image generation without extra inference overhead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.17354","ref_index":22,"ref_count":2,"confidence":0.55,"is_internal_anchor":false,"paper_title":"CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots","primary_cat":"cs.LG","submitted_at":"2025-05-23T00:12:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CT-OT Flow estimates continuous-time dynamics from discrete temporal snapshots by using partial optimal transport to align intervals and kernel smoothing to reconstruct distributions for ODE/SDE training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.11615","ref_index":36,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting","primary_cat":"cs.LG","submitted_at":"2025-03-14T17:35:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"In the Gaussian setting the Wasserstein error of score-matching-plus-diffusion sampling equals a kernel norm of the data power spectrum whose kernel is determined by the four error sources and the algorithm parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2412.06965","ref_index":49,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Improving Music Source Separation with Diffusion and Consistency Refinement","primary_cat":"cs.SD","submitted_at":"2024-12-09T20:09:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Diffusion-based refinement followed by consistency distillation improves music source separation quality and inference speed across U-Net and BS-RoFormer backbones on Slakh2100 and MUSDB18.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2412.03134","ref_index":29,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"A Probabilistic Formulation of Offset Noise in Diffusion Models","primary_cat":"stat.ML","submitted_at":"2024-12-04T08:57:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A diffusion model variant that adds structured non-zero-mean noise via modified forward/reverse processes, yielding an ELBO loss analogous to offset noise but with time-dependent coefficients, and showing gains on synthetic high-dimensional data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.13443","ref_index":64,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Nonlinear Assimilation via Score-based Sequential Langevin Sampling","primary_cat":"math.NA","submitted_at":"2024-11-20T16:31:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SSLS combines score-based Langevin Monte Carlo with annealing for nonlinear posterior updates in sequential assimilation, supported by total-variation convergence bounds that establish asymptotic stability and numerical tests in high-dimensional nonlinear settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.07430","ref_index":35,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"EventFlow: Forecasting Temporal Point Processes with Flow Matching","primary_cat":"cs.LG","submitted_at":"2024-10-09T20:57:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EventFlow applies flow matching to learn joint distributions over event times for temporal point processes, reporting 20-53% lower forecast error than autoregressive baselines on standard TPP benchmarks with fewer sampling calls.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.06940","ref_index":190,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","primary_cat":"cs.CV","submitted_at":"2024-10-09T14:34:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}