Tootfinder

PWD: Prior-Guided and Wavelet-Enhanced Diffusion Model for Limited-Angle CT
Yi Liu, Yiyang Wen, Zekun Zhou, Junqi Ma, Linghang Wang, Yucheng Yao, Liu Shi, Qiegen Liu
https://arxiv.org/abs/2507.05317

PWD: Prior-Guided and Wavelet-Enhanced Diffusion Model for Limited-Angle CT
Generative diffusion models have received increasing attention in medical imaging, particularly in limited-angle computed tomography (LACT). Standard diffusion models achieve high-quality image reconstruction but require a large number of sampling steps during inference, resulting in substantial computational overhead. Although skip-sampling strategies have been proposed to improve efficiency, they often lead to loss of fine structural details. To address this issue, we propose a prior informat…

Bridging Sequential Deep Operator Network and Video Diffusion: Residual Refinement of Spatio-Temporal PDE Solutions
Jaewan Park, Farid Ahmed, Kazuma Kobayashi, Seid Koric, Syed Bahauddin Alam, Iwona Jasiuk, Diab Abueidda
https://arxiv.org/abs/2507.06133

Bridging Sequential Deep Operator Network and Video Diffusion: Residual Refinement of Spatio-Temporal PDE Solutions
Video-diffusion models have recently set the standard in video generation, inpainting, and domain translation thanks to their training stability and high perceptual fidelity. Building on these strengths, we repurpose conditional video diffusion as a physics surrogate for spatio-temporal fields governed by partial differential equations (PDEs). Our two-stage surrogate first applies a Sequential Deep Operator Network (S-DeepONet) to produce a coarse, physics-consistent prior from the prescribed b…

Elementary discrete diffusion/redistancing schemes for the mean curvature flow
Antonin Chambolle, Daniele De Gennaro, Massimiliano Morini
https://arxiv.org/abs/2506.05946

Elementary discrete diffusion/redistancing schemes for the mean curvature flow
We consider here a fully discrete and explicit scheme for the mean curvature flow of boundaries, based on an elementary diffusion step and a precise redistancing operation. We give an elementary convergence proof for the scheme under the standard CFL condition $h\sim\varepsilon^2$, where $h$ is the time discretization step and $\varepsilon$ the space step. We discuss extensions to more general convolution/redistancing schemes.

Heat Transport and Dissipation in 2.5D Rotating Internally Heated and Cooled Convection
Tom Joshi-Hartley (University of Exeter), Matthew K. Browning (University of Exeter), Laura K. Currie (Durham University), Neil T. Lewis (University of Exeter), Benjamin P. Brown (University of Colorado at Boulder), Simon R. W. Lance (University of Exeter)
https:/…

Heat Transport and Dissipation in 2.5D Rotating Internally Heated and Cooled Convection
Models of astrophysical convection, such as mixing length theory, typically assume that the heat transport is independent of microphysical diffusivities. Such 'diffusion-free' behaviour is, however, not observed in numerical simulations employing standard fixed-flux or fixed-temperature boundary conditions, except possibly in extreme parameter regimes that are computationally expensive to achieve. Recent numerical and experimental work has suggested that internally heated and cooled convection …

DiWA: Diffusion Policy Adaptation with World Models
Akshay L Chandra, Iman Nematollahi, Chenguang Huang, Tim Welschehold, Wolfram Burgard, Abhinav Valada
https://arxiv.org/abs/2508.03645

DiWA: Diffusion Policy Adaptation with World Models
Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of real-world interactions, posing a major bottleneck for practical fine-tuning. Although prior work frames the denoising process in diffusion policies as a Markov Decision Process to enable RL-based updates, its strong dependence on environment interaction rema…

DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models
Saifullah Saifullah, Stefan Agne, Andreas Dengel, Sheraz Ahmed
https://arxiv.org/abs/2508.04208

DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models
As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems. While some recent works have explored Differential Privacy (DP) to mitigate these privacy risks, DP-based training is known to cause significant performance degradation and impose several limitations on standard training procedures, making its direct applicat…

Expanding the Standard Diffusion Process to Specified Non-Gaussian Marginal Distributions
Robert Richardson, H. Dennis Tolley, Kenneth Kuttler
https://arxiv.org/abs/2508.03617 h…

Expanding the Standard Diffusion Process to Specified Non-Gaussian Marginal Distributions
We develop a class of non-Gaussian translation processes that extend classical stochastic differential equations (SDEs) by prescribing arbitrary absolutely continuous marginal distributions. Our approach uses a copula-based transformation to flexibly model skewness, heavy tails, and other non-Gaussian features often observed in real data. We rigorously define the process, establish key probabilistic properties, and construct a corresponding diffusion model via stochastic calculus, including pro…

This https://arxiv.org/abs/2505.21179 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model
Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-Free Guidance (CFG) works well in standard settings, it fails under aggressive sampling step compression due to divergent predictions between positive and negative branches. We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based…

Beyond water limitation in vegetation-autotoxicity patterning: a cross-diffusion model
Francesco Giannino, Annalisa Iuorio, Cinzia Soresina
https://arxiv.org/abs/2506.03981

Beyond water limitation in vegetation-autotoxicity patterning: a cross-diffusion model
Many mathematical models describing vegetation patterns are based on biomass--water interactions, due to the impact of this limited resource in arid and semi-arid environments. However, in recent years, a novel biological factor called autotoxicity has proved to play a key role in vegetation spatiotemporal dynamics, particularly by inhibiting biomass growth and increasing its natural mortality rate. In a standard reaction-diffusion framework, biomass-toxicity dynamics alone are unable to suppor…

Quenching time and probability estimates for a stochastic reaction-diffusion system with coupled inner singular absorption terms driven by mixed noises
Nikos I. Kavallaris, Christos V. Nikolopoulos, Subramani Sankar
https://arxiv.org/abs/2508.03354

Quenching time and probability estimates for a stochastic reaction-diffusion system with coupled inner singular absorption terms driven by mixed noises
This paper investigates a stochastic parabolic system under Robin boundary conditions, for which the deterministic counterpart exhibits finite quenching. The stochastic system incorporates mixed noise, combining standard one-dimensional Brownian motion and fractional Brownian motion. Under appropriate assumptions, we derive explicit lower and upper bounds for the quenching time of the solution and establish the global existence of a weak solution. Leveraging Malliavin calculus, we further obtai…

Simple holograpic dual of the Maxwell-Cattaneo model
Yongjun Ahn, Matteo Baggioli, Yanyan Bu, Masataka Matsumoto, Xiyang Sun
https://arxiv.org/abs/2506.00926

Simple holograpic dual of the Maxwell-Cattaneo model
Diffusion, as described by Fick's laws, governs the spreading of particles, information, data, and even financial fluctuations. However, due to its parabolic structure, the diffusion equation leads to an unphysical prediction: any localized disturbance instantaneously affects the entire system. The Maxwell-Cattaneo (MC) model, originally introduced to address relativistic heat conduction, refines the standard diffusion framework by incorporating a finite relaxation time $τ$, associated with th…

Filtering and 1/3 Power Law for Optimal Time Discretisation in Numerical Integration of Stochastic Differential Equations
Igor G. Vladimirov
https://arxiv.org/abs/2508.03135 htt…

Filtering and 1/3 Power Law for Optimal Time Discretisation in Numerical Integration of Stochastic Differential Equations
This paper is concerned with the numerical integration of stochastic differential equations (SDEs) which govern diffusion processes driven by a standard Wiener process. With the latter being replaced by a sequence of increments at discrete moments of time, we revisit a filtering point of view on the approximate strong solution of the SDE as an estimate of the hidden system state whose conditional probability distribution is updated using a Bayesian approach and Brownian bridges over the interme…

Constructing Generalized Sample Transition Probabilities with Biased Simulations
Yanbin Wang, Jakub Rydzewski, Ming Chen
https://arxiv.org/abs/2508.03977 https://

Constructing Generalized Sample Transition Probabilities with Biased Simulations
In molecular dynamics (MD) simulations, accessing transition probabilities between states is crucial for understanding kinetic information, such as reaction paths and rates. However, standard MD simulations are hindered by the capacity to visit the states of interest, prompting the use of enhanced sampling to accelerate the process. Unfortunately, biased simulations alter the inherent probability distributions, making kinetic computations using techniques such as diffusion maps challenging. Her…

From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC
Jingsong Liu, Xiaofeng Deng, Han Li, Azar Kazemi, Christian Grashei, Gesa Wilkens, Xin You, Tanja Groll, Nassir Navab, Carolin Mogler, Peter J. Sch\"uffler
https://arxiv.org/abs/2508.02528

From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC
Hematoxylin and eosin (H&E) staining is the clinical standard for assessing tissue morphology, but it lacks molecular-level diagnostic information. In contrast, immunohistochemistry (IHC) provides crucial insights into biomarker expression, such as HER2 status for breast cancer grading, but remains costly and time-consuming, limiting its use in time-sensitive clinical workflows. To address this gap, virtual staining from H&E to IHC has emerged as a promising alternative, yet faces two core chal…

A micromorphic-based artificial diffusion method for stabilized finite element approximation of convection-diffusion problems
Soheil Firooz, B. Daya Reddy, Paul Steinmann
https://arxiv.org/abs/2506.14800

A micromorphic-based artificial diffusion method for stabilized finite element approximation of convection-diffusion problems
We present a novel artificial diffusion method to circumvent the instabilities associated with the standard finite element approximation of convection-diffusion equations. Motivated by the micromorphic approach, we introduce an auxiliary variable, which is related to the gradient of the field of interest, and which leads to a coupled problem. Conditions for well-posedness of the resulting formulation are established. We carry out a comprehensive numerical study to compare the proposed methodolo…

This https://arxiv.org/abs/2411.04178 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Breaking boundaries: extending the orbit-averaged Fokker-Planck equation inside the loss cone
In this Letter, we present a new formulation of loss cone theory as a reaction-diffusion system, which accounts for loss cone events through a sink term and can be orbit-averaged. It can recover the standard approach based on boundary conditions, and is derived from a simple physical model that overcomes many of the classical theoretical constraints. We test our formulation by computing the relaxed distribution of disruptive orbits in phase space, that has a simple analytic form and matches the…

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
Feng Hong, Geng Yu, Yushi Ye, Haicheng Huang, Huangjie Zheng, Ya Zhang, Yanfeng Wang, Jiangchao Yao
https://arxiv.org/abs/2507.18578

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models, designed for fast parallel generation. However, existing DLLMs are plagued by a severe quality-speed trade-off, where faster parallel decoding leads to significant performance degradation. We attribute this to the irreversibility of standard decoding in DLLMs, which is easily polarized into the wrong decoding direction along with early error context accumulation. To resolve this, we introd…

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
Renhang Liu, Chia-Yu Hung, Navonil Majumder, Taylor Gautreaux, Amir Ali Bagherzadeh, Chuan Li, Dorien Herremans, Soujanya Poria
https://arxiv.org/abs/2507.20880

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
Diffusion and flow-matching models have revolutionized automatic text-to-audio generation in recent times. These models are increasingly capable of generating high quality and faithful audio outputs capturing to speech and acoustic events. However, there is still much room for improvement in creative audio generation that primarily involves music and songs. Recent open lyrics-to-song models, such as, DiffRhythm, ACE-Step, and LeVo, have set an acceptable standard in automatic song generation fo…

This https://arxiv.org/abs/2505.22623 has been replaced.
initial toot: https://mastoxiv.page/@ar…

A theory for diffusion-controlled reactions within nonequilibrium steady-states
We study diffusion-controlled processes in nonequilibrium steady-states, where standard rate theory assumptions break down. Using transition path theory, we generalize the relations between reactive probability fluxes and measures of the rate of the reaction. Stochastic thermodynamics analysis reveals how work constrains the enhancement of rates relative to their equilibrium values. An analytically solvable ion-pairing model under a strong electric field illustrates and validates our approach a…

Zigzagging Diffusion and Non-Standard Transport in Particle-laden Nanopores Under Extreme Confinement
A. Baer, P. Malgaretti, K. Hoellring, J. Harting, Ana-Suncana Smith
https://arxiv.org/abs/2506.09191

Zigzagging Diffusion and Non-Standard Transport in Particle-laden Nanopores Under Extreme Confinement
Understanding transport subject to molecular-scale confinement is key to advancing nanofluidics, yet classical hydrodynamic laws often fail at these scales. Here, we study a model system: transport of toluene as a solvent and small fullerenes as model particles confined within alumina slit nanopores using molecular dynamics simulations. We find that toluene organizes into discrete layers whose commensurability with the pore width leads to a striking, non-monotonic, zig-zag dependence of transpo…

Implicit neural representations for accurate estimation of the standard model of white matter
Tom Hendriks, Gerrit Arends, Edwin Versteeg, Anna Vilanova, Maxime Chamberland, Chantal M. W. Tax
https://arxiv.org/abs/2506.15762

Implicit neural representations for accurate estimation of the standard model of white matter
Diffusion magnetic resonance imaging (dMRI) enables non-invasive investigation of tissue microstructure. The Standard Model (SM) of white matter aims to disentangle dMRI signal contributions from intra- and extra-axonal water compartments. However, due to the model its high-dimensional nature, extensive acquisition protocols with multiple b-values and diffusion tensor shapes are typically required to mitigate parameter degeneracies. Even then, accurate estimation remains challenging due to nois…

Comparison between the diffusion properties of different small-scale fractional transport models
Paolo Cifani, Franco Flandoli
https://arxiv.org/abs/2506.08068

Comparison between the diffusion properties of different small-scale fractional transport models
Stochastic transport due to a velocity field modeled by the superposition of small-scale divergence free vector fields activated by Fractional Gaussian Noises (FGN) is numerically investigated. We present two non-trivial contributions: the first one is the definition of a model where different space-time structures can be compared on the same ground: this is achieved by imposing the same average kinetic energy to a standard Ornstein-Uhlenbeck approximation, then taking the limit to the idealize…

A theory for diffusion-controlled reactions within nonequilibrium steady-states
Seokjin Moon, David T. Limmer
https://arxiv.org/abs/2505.22623 https://

A theory for diffusion-controlled reactions within nonequilibrium steady-states
We study diffusion-controlled processes in nonequilibrium steady-states, where standard rate theory assumptions break down. Using transition path theory, we generalize the relations between reactive probability fluxes and measures of the rate of the reaction. Stochastic thermodynamics analysis reveals how work constrains the enhancement of rates relative to their equilibrium values. An analytically solvable ion-pairing model under a strong electric field illustrates and validates our approach a…

Pathwise analysis of log-optimal portfolios
Andrew L. Allan, Anna P. Kwossek, Chong Liu, David J. Pr\"omel
https://arxiv.org/abs/2507.18232 https://ar…

Pathwise analysis of log-optimal portfolios
Based on the theory of càdlàg rough paths, we develop a pathwise approach to analyze stability and approximation properties of portfolios along individual price trajectories generated by standard models of financial markets. As a prototypical example from portfolio theory, we study the log-optimal portfolio in a classical investment-consumption optimization problem on a frictionless financial market modelled by an Itô diffusion process. We identify a fully deterministic framework that enable…

VITA: Vision-to-Action Flow Matching Policy
Dechen Gao, Boqi Zhao, Andrew Lee, Ian Chuang, Hanchu Zhou, Hang Wang, Zhe Zhao, Junshan Zhang, Iman Soltani
https://arxiv.org/abs/2507.13231

VITA: Vision-to-Action Flow Matching Policy
We present VITA, a Vision-To-Action flow matching policy that evolves latent visual representations into latent actions for visuomotor control. Traditional flow matching and diffusion policies sample from standard source distributions (e.g., Gaussian noise) and require additional conditioning mechanisms like cross-attention to condition action generation on visual information, creating time and space overheads. VITA proposes a novel paradigm that treats latent images as the flow source, learnin…

A Wave-type Model for Age- and Space-structured Epidemics
Nicolas Schlosser
https://arxiv.org/abs/2507.19252 https://arxiv.org/pdf/2507.19252

A Wave-type Model for Age- and Space-structured Epidemics
We introduce a novel approach of epidemic modeling by combining age-structured models with damped wave equations. This transforms the parabolic-type reaction-diffusion model into a hyperbolic system that shares many properties with a wave or telegrapher's equation. After we establish the existence of a weak solution of the resulting partial differential equation by means of characteristics, we show that the solutions to the new model converge to a solution of the standard age-dependent reaction…

Conservative data-driven finite element formulation
Adriana Kulikov\'a (Glasgow Computational Engineering Centre), Andrei G. Shvarts (Glasgow Computational Engineering Centre), {\L}ukasz Kaczmarczyk (Glasgow Computational Engineering Centre), Chris J. Pearce (Glasgow Computational Engineering Centre)
https://arxiv.org/abs/25…

Conservative data-driven finite element formulation
This paper presents a new data-driven finite element framework derived with mixed finite element formulation. The standard approach to diffusion problems requires the solution of the mathematical equations that describe both the conservation law and the constitutive relations, where the latter is traditionally obtained after fitting experimental data to simplified material models. To exploit all available information and avoid bias in the material model, we follow a data-driven approach. While …

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Zhifeng Wang, Renjiao Yi, Xin Wen, Chenyang Zhu, Kai Xu, Kunlun He
https://arxiv.org/abs/2506.19455

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography …

SDEs with critical general distributional drifts: sharp solvability and blow ups
D. Kinzebulatov, R. Vafadar
https://arxiv.org/abs/2506.09244 https://

SDEs with critical general distributional drifts: sharp solvability and blow ups
We establish weak well-posedness for SDEs having discontinuous diffusion coefficients and general distributional drifts that may introduce blow up effects. Our drifts satisfy minimal assumptions, i.e.\,we assume only that the Cauchy problem for the Kolmogorov backward equation is well-posed in the standard Hilbert triple $W^{1,2} \hookrightarrow L^2 \hookrightarrow W^{-1,2}$. By a result of Mazya and Verbitsky, these assumptions are precisely those drifts that can be represented as the sum of a…

This https://arxiv.org/abs/2502.13574 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
Denoising diffusion probabilistic models (DDPMs) can be utilized to recover a clean signal from its degraded observation(s) by conditioning the model on the degraded signal. The degraded signals are themselves contaminated versions of the clean signals; due to this correlation, they may encompass certain useful information about the target clean data distribution. However, existing adoption of the standard Gaussian as the prior distribution in turn discards such information when shaping the pri…

MAMBO: High-Resolution Generative Approach for Mammography Images
Milica \v{S}kipina, Nikola Jovi\v{s}i\'c, Nicola Dall'Asen, Vanja \v{S}venda, Anil Osman Tur, Slobodan Ili\'c, Elisa Ricci, Dubravko \'Culibrk
https://arxiv.org/abs/2506.08677

MAMBO: High-Resolution Generative Approach for Mammography Images
Mammography is the gold standard for the detection and diagnosis of breast cancer. This procedure can be significantly enhanced with Artificial Intelligence (AI)-based software, which assists radiologists in identifying abnormalities. However, training AI systems requires large and diverse datasets, which are often difficult to obtain due to privacy and ethical constraints. To address this issue, the paper introduces MAMmography ensemBle mOdel (MAMBO), a novel patch-based diffusion approach des…