Tootfinder

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
Kaiwen Zheng, Yuji Wang, Qianli Ma, Huayu Chen, Jintao Zhang, Yogesh Balaji, Jianfei Chen, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang
https://arxiv.org/abs/2510.08431

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
This work represents the first effort to scale up continuous-time consistency distillation to general application-level image and video diffusion models. Although continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of standard evaluation …

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…

McKean-Vlasov limits of scaling-critical reaction-diffusion equations with random initial data
Bryan Castillo, Alexander Dunlap
https://arxiv.org/abs/2509.06260 https://

McKean-Vlasov limits of scaling-critical reaction-diffusion equations with random initial data
We study a large class of scaling-critical reaction-diffusion equations in two spatial dimensions, where the initial data is white noise mollified at scale $\varepsilon^2$ and the reaction term is attenuated by a factor of $(\log\varepsilon^{-1})^{-1}$. We show that as $\varepsilon\to 0$, the solution converges to the solution of a McKean-Vlasov equation, which is Gaussian with standard deviation given by the solution to an ODE. Our result covers the case of the reaction term $f(u)=u^3$, and th…

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
Huangjie Zheng, Shansan Gong, Ruixiang Zhang, Tianrong Chen, Jiatao Gu, Mingyuan Zhou, Navdeep Jaitly, Yizhe Zhang
https://arxiv.org/abs/2510.01329

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps. We introduce Continuously Augmented Discrete Diffusion (CADD), a framework that augments the discrete state space with a paired diffusion in a continuous latent space. This yields graded, gradually corrupted states in which masked tokens a…

Non-Identical Diffusion Models in MIMO-OFDM Channel Generation
Yuzhi Yang, Omar Alhussein, M\'erouane Debbah
https://arxiv.org/abs/2509.01641 https://a…

Non-Identical Diffusion Models in MIMO-OFDM Channel Generation
We propose a novel diffusion model, termed the non-identical diffusion model, and investigate its application to wireless orthogonal frequency division multiplexing (OFDM) channel generation. Unlike the standard diffusion model that uses a scalar-valued time index to represent the global noise level, we extend this notion to an element-wise time indicator to capture local error variations more accurately. Non-identical diffusion enables us to characterize the reliability of each element (e.g., …

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…

Tree-Guided Diffusion Planner
Hyeonseong Jeon, Cheolhong Min, Jaesik Park
https://arxiv.org/abs/2508.21800 https://arxiv.org/pdf/2508.21800

Tree-Guided Diffusion Planner
Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. However, standard gradient guidance typically performs optimally under convex and differentiable reward landscapes, showing substantially reduced effectiveness in real-world scenarios involving non-convex objectives, non-differentiable constraints, and multi-reward structures. Furthermore, recent supervised planning approaches require task-specific training or value estim…

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…

Aydogan Ozcan at the University of California, Los Angeles, and his colleagues have developed a diffusion-based
image generator that works using a beam of light.
While the encoding process is digital, requiring a small amount of energy,
the decoding process is entirely light-based, requiring no computational power.
“Unlike digital diffusion models that require hundreds to thousands of iterative steps,
this process achieves image generation in a snapshot,
…

Light-based AI image generator uses almost no power
A system that generates images by inducing random fluctuations in a laser beam could slash energy use compared with standard AI tools

Steady-State Spread Bounds for Graph Diffusion via Laplacian Regularisation
Ardavan Rahimian
https://arxiv.org/abs/2510.04924 https://arxiv.org/pdf/2510.04…

Steady-State Spread Bounds for Graph Diffusion via Laplacian Regularisation
We study how far a diffusion process on a graph can drift from a designed starting pattern when that pattern is produced using Laplacian regularisation. Under standard stability conditions for undirected, entrywise nonnegative graphs, we give a closed-form, instance-specific upper bound on the steady-state spread, measured as the relative change between the final and initial profiles. The bound separates two effects: (i) an irreducible term determined by the graph's maximum node degree, and (ii…

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
Thanh Nguyen, Chang D. Yoo
https://arxiv.org/abs/2508.13904 https://

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
The generative power of diffusion models (DMs) has recently enabled high-performing decision-making algorithms in offline reinforcement learning (RL), achieving state-of-the-art results across standard benchmarks. Among them, Diffusion Q-Learning (DQL) stands out as a leading method for its consistently strong performance. Nevertheless, DQL remains limited in practice due to its reliance on multi-step denoising for action generation during both training and inference. Although one-step denoisin…

Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet
https://arxiv.org/abs/2510.03929 https://arxiv.org/pdf/2…

Self-Speculative Masked Diffusions
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore n…

CRISP - Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation
Daniel San Jos\'e Pro, Oliver Hausd\"orfer, Ralf R\"omer, Maximilian D\"osch, Martin Schuck, Angela P. Sch\"ollig
https://arxiv.org/abs/2509.06819

CRISP - Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation
Learning-based controllers, such as diffusion policies and vision-language action models, often generate low-frequency or discontinuous robot state changes. Achieving smooth reference tracking requires a low-level controller that converts high-level targets commands into joint torques, enabling compliant behavior during contact interactions. We present CRISP, a lightweight C++ implementation of compliant Cartesian and joint-space controllers for the ROS2 control standard, designed for seamless …

Turing instability and 2-D pattern formation in reaction-diffusion systems derived from kinetic theory
Stefano Boccelli, Giorgio Martal\`o, Romina Travaglini
https://arxiv.org/abs/2509.20268

Turing instability and 2-D pattern formation in reaction-diffusion systems derived from kinetic theory
We investigate Turing instability and pattern formation in two-dimensional domains for two reaction-diffusion models, obtained as diffusive limits of kinetic equations for mixtures of monatomic and polyatomic gases. The first model is of Brusselator type, which, compared with the classical formulation, presents an additional parameter whose role in stability and pattern formation is discussed. In the second framework, the system exhibits standard nonlinear diffusion terms typical of predator-pr…

Asymmetric Diffusion Recommendation Model
Yongchun Zhu, Guanyu Jiang, Jingwu Chen, Feng Zhang, Xiao Yang, Zuotao Liu
https://arxiv.org/abs/2508.12706 https://

Asymmetric Diffusion Recommendation Model
Recently, motivated by the outstanding achievements of diffusion models, the diffusion process has been employed to strengthen representation learning in recommendation systems. Most diffusion-based recommendation models typically utilize standard Gaussian noise in symmetric forward and reverse processes in continuous data space. Nevertheless, the samples derived from recommendation systems inhabit a discrete data space, which is fundamentally different from the continuous one. Moreover, Gaussi…

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…

Stationarity preserving nodal Finite Element methods for multi-dimensional linear hyperbolic balance laws via a Global Flux quadrature formulation
Wasilij Barsukow, Mario Ricchiuto, Davide Torlo
https://arxiv.org/abs/2510.02928

Stationarity preserving nodal Finite Element methods for multi-dimensional linear hyperbolic balance laws via a Global Flux quadrature formulation
We consider linear, hyperbolic systems of balance laws in several space dimensions. They possess non-trivial steady states, which result from the equilibrium between derivatives of the unknowns in different directions, and the sources. Standard numerical methods fail to account for this equilibrium, and include stabilization that destroys it. This manifests itself in a diffusion of states that are sup- posed to remain stationary. We derive new stabilized high-order Finite Element methods based …

Calibrated Semantic Diffusion: A p-Laplacian Synthesis with Learnable Dissipation, Quantified Constants, and Graph-Aware Calibration
Faruk Alpay, Hamdi Alakkad
https://arxiv.org/abs/2508.13658

Calibrated Semantic Diffusion: A p-Laplacian Synthesis with Learnable Dissipation, Quantified Constants, and Graph-Aware Calibration
We develop a calibrated diffusion framework by synthesizing three established concepts: linear Laplacian smoothing, nonlinear graph p-Laplacian flows, and a learnable dissipation term derived from a strongly convex potential. This synthesis provides a general model for graph-based diffusion with controllable dynamics. Our key theoretical results include a quantified two-regime decay analysis for $p>2$, which provides stronger, p-dependent transient bounds not captured by standard ISS templates,…

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…

Axion-Photon Conversion In Magnetized Universe: Impact On The Global 21-cm Signal
Pravin Kumar Natwariya, Vivekanand Mohapatra, Hriditi Howlader
https://arxiv.org/abs/2509.04237

Axion-Photon Conversion In Magnetized Universe: Impact On The Global 21-cm Signal
The reported anomalous global 21-cm signal $(T_{21})$ from the cosmic dawn era by Experiment to Detect the Global Epoch of Reionisation Signature (EDGES) could hint towards new physics beyond the standard model. The resonant conversion of the axion-like particles (ALPs) into photons in the presence of primordial magnetic fields (PMFs) could be a viable solution. However, the strength of the PMFs can change over the time as they can decay by ambipolar diffusion and turbulent decay. Consequently,…

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…

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…

Neural Jump ODEs as Generative Models
Robert A. Crowell, Florian Krach, Josef Teichmann
https://arxiv.org/abs/2510.02757 https://arxiv.org/pdf/2510.02757…

Neural Jump ODEs as Generative Models
In this work, we explore how Neural Jump ODEs (NJODEs) can be used as generative models for Itô processes. Given (discrete observations of) samples of a fixed underlying Itô process, the NJODE framework can be used to approximate the drift and diffusion coefficients of the process. Under standard regularity assumptions on the Itô processes, we prove that, in the limit, we recover the true parameters with our approximation. Hence, using these learned coefficients to sample from the correspond…

Optimal control of SDEs with merely measurable drift: an HJB approach
Kai Du, Qingmeng Wei
https://arxiv.org/abs/2509.01054 https://arxiv.org/pdf/2509.0105…

Optimal control of SDEs with merely measurable drift: an HJB approach
We investigate an optimal control problem for a diffusion whose drift and running cost are merely measurable in the state variable. Such low regularity rules out the use of Pontryagin's maximum principle and also invalidates the standard proof of the Bellman principle of optimality. We address these difficulties by analyzing the associated Hamilton-Jacobi-Bellman (HJB) equation. Using PDE techniques together with a policy iteration scheme, we prove that the HJB equation admits a unique strong s…

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…

Solving time-fractional diffusion equations with Robin boundary conditions via fractional Hamiltonian boundary value methods
Qian Luo, Aiguo Xiao, Xiaoqiang Yan, Jingmin Xia
https://arxiv.org/abs/2509.17793

Solving time-fractional diffusion equations with Robin boundary conditions via fractional Hamiltonian boundary value methods
In this paper, we propose a novel numerical scheme for solving time-fractional reaction-diffusion problems with Robin boundary conditions, where the time derivative is in the Caputo sense of order $α\in(0,1)$. The existence and uniqueness of the solution is proved. Our proposed method is based on the spectral collocation method in space and Fractional Hamiltonian boundary value methods in time. For the considered spectral collocation method, the basis functions used are not the standard polyno…

Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning
Tianchong Jiang, Jingtian Ji, Xiangshan Tan, Jiading Fang, Anand Bhattad, Vitor Guizilini, Matthew R. Walter
https://arxiv.org/abs/2510.02268

Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning
We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics. Using Plucker embeddings of per-pixel rays, we show that conditioning on extrinsics significantly improves generalization across viewpoints for standard behavior cloning policies, including ACT, Diffusion Policy, and SmolVLA. To evaluate policy robustness under realistic viewpoint shifts, we introduce six manipulation tasks in RoboSuite and ManiSkill that pair "fixed" and "randomized" scene vari…

Pairwise correlations of global times in one-dimensional Brownian motion under stochastic resetting
Yihao Wang, Hanshuang Chen
https://arxiv.org/abs/2508.11387 https://

Pairwise correlations of global times in one-dimensional Brownian motion under stochastic resetting
Brownian motion with stochastic resetting-a process combining standard diffusion with random returns to a fixed position-has emerged as a powerful framework with applications spanning statistical physics, chemical kinetics, biology, and finance. In this study, we investigate the mutual correlations among three global characteristic times for one-dimensional resetting Brownian motion $x(τ)$ over the interval $τ\in \left[ 0, t\right] $: the occupation time $t_o$ spent on the positive semi-axis,…

A Statistical Benchmark for Diffusion Posterior Sampling Algorithms
Martin Zach, Youssef Haouchat, Michael Unser
https://arxiv.org/abs/2509.12821 https://a…

A Statistical Benchmark for Diffusion Posterior Sampling Algorithms
We propose a statistical benchmark for diffusion posterior sampling (DPS) algorithms for Bayesian linear inverse problems. The benchmark synthesizes signals from sparse Lévy-process priors whose posteriors admit efficient Gibbs methods. These Gibbs methods can be used to obtain gold-standard posterior samples that can be compared to the samples obtained by the DPS algorithms. By using the Gibbs methods for the resolution of the denoising problems in the reverse diffusion, the framework also is…

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…

An efficient spline-based scheme on Shishkin-type meshes for solving singularly perturbed coupled systems with Robin boundary conditions
Kousalya Ramanujam, Vembu Shanthi
https://arxiv.org/abs/2509.01575

An efficient spline-based scheme on Shishkin-type meshes for solving singularly perturbed coupled systems with Robin boundary conditions
In this paper, we investigate a weakly coupled system of singularly perturbed linear reaction-diffusion equations with Robin boundary conditions, where the leading terms are multiplied by small positive parameters that may differ in magnitude. The solution to this system exhibits overlapping and interacting boundary layers. To appropriately resolve these layers, we employ a standard Shishkin mesh and propose a novel modification of Bakhvalov-Shishkin mesh. A cubic spline approximation is applie…

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…

MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Dayi Dong, Maulik Bhatt, Seoyeon Choi, Negar Mehr
https://arxiv.org/abs/2509.14159

MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. We propose to learn such behaviors from expert demonstrations via imitation learning (IL). However, when expert demonstrations are multi-modal, standard IL approaches can struggle to capture the diverse strategies, hindering effective coordination. Diffusion models are known to be effective at handling complex multi-modal tr…

Anchored Langevin Algorithms
Mert Gurbuzbalaban, Hoang M. Nguyen, Xicheng Zhang, Lingjiong Zhu
https://arxiv.org/abs/2509.19455 https://arxiv.org/pdf/2509.…

Anchored Langevin Algorithms
Standard first-order Langevin algorithms such as the unadjusted Langevin algorithm (ULA) are obtained by discretizing the Langevin diffusion and are widely used for sampling in machine learning because they scale to high dimensions and large datasets. However, they face two key limitations: (i) they require differentiable log-densities, excluding targets with non-differentiable components; and (ii) they generally fail to sample heavy-tailed targets. We propose anchored Langevin dynamics, a unif…

Adaptive least-squares space-time finite element methods for convection-diffusion problems
Christian K\"othe, Olaf Steinbach
https://arxiv.org/abs/2509.11955 https://

Adaptive least-squares space-time finite element methods for convection-diffusion problems
In this paper we formulate and analyse adaptive (space-time) least-squares finite element methods for the solution of convection-diffusion equations. The convective derivative $\mathbf{v} \cdot \nabla u$ is considered as part of the total time derivative $\frac{d}{dt}u = \partial_t u + \mathbf{v} \cdot \nabla u$, and therefore we can use a rather standard stability and error analysis for related space-time finite element methods. For stationary problems we restrict the ansatz space $H^1_0(Ω)$ …

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li, Huaping Liu
https://arxiv.org/abs/2509.14889

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackles key limitations of prior VLAs, including domain overfitting, non-interpretable reasoning, and the high latency of auxiliary generative models, by integrating VLM-based reflective reasoning with diffusion-based action generation under a mixture-of-experts design. Through a two-stage training recipe of action groundin…

Radiolunadiff: Estimation of wireless network signal strength in lunar terrain
Paolo Torrado, Anders Pearson, Jason Klein, Alexander Moscibroda, Joshua Smith
https://arxiv.org/abs/2509.14559

Radiolunadiff: Estimation of wireless network signal strength in lunar terrain
In this paper, we propose a novel physics-informed deep learning architecture for predicting radio maps over lunar terrain. Our approach integrates a physics-based lunar terrain generator, which produces realistic topography informed by publicly available NASA data, with a ray-tracing engine to create a high-fidelity dataset of radio propagation scenarios. Building on this dataset, we introduce a triplet-UNet architecture, consisting of two standard UNets and a diffusion network, to model compl…

A stability-enhanced nonstandard finite difference framework for solving one and two-dimensional nonlocal differential equations
Shweta Kumari, Mani Mehra
https://arxiv.org/abs/2508.13542

A stability-enhanced nonstandard finite difference framework for solving one and two-dimensional nonlocal differential equations
Standard finite difference (SFD) schemes often suffer from limited stability regions, especially when applied in explicit setup to partial differential equations. To address this challenge, this study investigates the efficacy of nonstandard finite difference (NSFD) schemes in enhancing stability of explicit SFD schemes for 1D and 2D Caputo-type time-fractional diffusion equations (TFDEs). A nonstandard L1approximation is proposed for the Caputo fractional derivative, and its local truncation e…

Error analysis of a fully discrete structure-preserving finite element scheme for a diffuse-interface model of tumour growth
Agus L. Soenjaya, Ping Lin, Thanh Tran
https://arxiv.org/abs/2509.14486

Error analysis of a fully discrete structure-preserving finite element scheme for a diffuse-interface model of tumour growth
We develop a fully discrete structure-preserving finite element method for a diffuse-interface model of tumour growth. The system couples a Cahn--Hilliard type equation with a nonlinear reaction-diffusion equation for nutrient concentration and admits a dissipative energy law at the continuous level. For the discretisation, we employ a scalar auxiliary variable (SAV) formulation together with a mixed finite element method for the Cahn--Hilliard part and standard conforming finite elements for t…