Diffusion posterior samplers produce biased outputs that can be expressed as an Ornstein-Uhlenbeck path expectation via a surrogate Gaussian path and Feynman-Kac representation, with STSL flattening the spatially varying bias term.
hub Canonical reference
International Conference on Learning Representations , year=
Canonical reference. 71% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 5
method 2
citation-polarity summary
representative citing papers
Quotient-space diffusion models generate correct symmetric distributions by removing redundancy on the quotient space, simplifying learning and improving results on small molecules and proteins under SE(3) symmetry.
Normalizing flows are constructed by learning the velocity of a stochastic interpolant via a quadratic loss derived from its probability current, yielding an efficient ODE-based alternative to diffusion models.
OM-Path uses Onsager-Machlup-regularized posterior transport on Doob-bridged paths for DGP inference and reports statistical wins over DBVI on the two largest UCI regression benchmarks.
Introduces adjoint-equation framework establishing dimension-free convergence bounds in any IPM for discrete diffusion models under masked and uniform priors.
DiHAL uses geometry proxies to pick where to replace the lower layers of a pretrained transformer with a diffusion bridge for hidden-state reconstruction, improving over token-level diffusion baselines on 8B models.
Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
Kernel-gradient drifting reformulates drifting models via kernel gradients to yield identifiable one-step generation with smoothed score matching and KL descent on Euclidean, Riemannian, and discrete spaces.
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.
The Sinkhorn treatment effect is a new entropic optimal transport measure of divergence between counterfactual distributions that admits first- and second-order pathwise differentiability, debiased estimators, and asymptotically valid tests for distributional treatment effects.
STMD distills the full transition map of diffusion sampling SDEs into a conditional Mean Flow model to enable fast one- or few-step stochastic sampling without teacher models or bi-level optimization.
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
A 130M-parameter continuous bitstream diffusion model with entropy-gated Langevin sampling achieves GenPPL 59.76 on LM1B and 27.06 on OWT, closing the gap to autoregressive models at matched entropy with 256 NFEs.
SSDMs introduce an intrinsic score-based diffusion framework on the Fubini-Study manifold to sample quantum pure-state ensembles without classical re-preparation.
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
Unbalanced Schrödinger Bridge (USB) provides a tractable, simulation-free solution to the Branching Schrödinger Bridge problem for modeling discrete birth-death dynamics at single-cell resolution from snapshot data.
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
Coupled initial noises in diffusion models, with designed dependence but unchanged marginal Gaussians, improve generated image diversity on Stable Diffusion variants while preserving quality and alignment.
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
citing papers explorer
-
Stochastic Schr\"odinger Diffusion Models for Pure-State Ensemble Generation
SSDMs introduce an intrinsic score-based diffusion framework on the Fubini-Study manifold to sample quantum pure-state ensembles without classical re-preparation.
-
RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction
RNA-FM is a flow-matching generative model that predicts genome-wide bulk RNA-seq expression from WSIs by learning a conditional velocity field, outperforming deterministic baselines.