Tootfinder

Condition number for finite element discretisation of nonlocal PDE systems with applications to biology
Olusegun E. Adebayo, Raluca Eftimie, Dumitru Trucu
https://arxiv.org/abs/2508.09781

Condition number for finite element discretisation of nonlocal PDE systems with applications to biology
In this work, we investigate the condition number for a system of coupled non-local reaction-diffusion-advection equations developed in the context of modelling normal and abnormal wound healing. Following a finite element discretisation of the coupled non-local system, we establish bounds for this condition number. We further discuss how model parameter choices affect the conditioning of the system. Finally, we discuss how the step size of the chosen time-stepping scheme and the spatial gr…

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
Chaojun Ni, Guosheng Zhao, Xiaofeng Wang, Zheng Zhu, Wenkang Qin, Xinze Chen, Guanghong Jia, Guan Huang, Wenjun Mei
https://arxiv.org/abs/2508.08170

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial simulation-to-reality (sim2real) gap. To bridge this gap, some approaches utilize scene reconstruction techniques to create photorealistic environments as a simulator. While this improves realistic sensor simulation, these methods are inherently constrained b…

The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
Leo Zhang
https://arxiv.org/abs/2508.04884 https://arxiv.org/pdf/2508.04884

The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
In this work, we study the problem of choosing the discretisation schedule for sampling from masked discrete diffusion models in terms of the information geometry of the induced probability path. Specifically, we show that the optimal schedule under the Fisher-Rao geometry recovers the popularly-used cosine schedule.

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Stephen Ni-Hahn, Chao P\'eter Yang, Mingchen Ma, Cynthia Rudin, Simon Mak, Yue Jiang
https://arxiv.org/abs/2510.10249

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Artificial Intelligence (AI) for music generation is undergoing rapid developments, with recent symbolic models leveraging sophisticated deep learning and diffusion model algorithms. One drawback with existing models is that they lack structural cohesion, particularly on harmonic-melodic structure. Furthermore, such existing models are largely "black-box" in nature and are not musically interpretable. This paper addresses these limitations via a novel generative music framework that incorporate…

Convergence rate for Fluctuations of mean field interacting diffusion and application to 2D viscous Vortex model and Coulomb potential
Alekos Cecchin, Paul Nikolaev
https://arxiv.org/abs/2509.01266

Convergence rate for Fluctuations of mean field interacting diffusion and application to 2D viscous Vortex model and Coulomb potential
For a system of mean field interacting diffusion on $\mathbb{T}^d$, the empirical measure $μ^N$ converges to the solution $μ$ of the Fokker-Planck equation. Refining this mean field limit as a Central Limit Theorem, the fluctuation process $ρ^N_t= \sqrt{N}( μ^N_t -μ_t)$ convergences to the solution $ρ$ of a linear stochastic PDE on the negative Sobolev space $H^{-λ-2}(\mathbb{T}^d)$. The main result of the paper is to establish a rate for such convergence: we show that $|\mathbb{E}[…

X got too much even for the Communications of the ACM
"The X platform has become an echo chamber for disinformation, hate speech, amplifying division, conspiracy theories, and more "
https://cacm.acm.org/opinion/deleting-x-why-sigdoc-left-the-platform/

Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation
Zijun Zhan, Yaxian Dong, Daniel Mawunyo Doe, Yuqing Hu, Shuai Li, Shaohua Cao, Zhu Han
https://arxiv.org/abs/2508.03464

Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation
With the rapid growth in demand for AI-generated content (AIGC), edge AIGC service providers (ASPs) have become indispensable. However, designing incentive mechanisms that motivate ASPs to deliver high-quality AIGC services remains a challenge, especially in the presence of information asymmetry. In this paper, we address bonus design between a teleoperator and an edge ASP when the teleoperator cannot observe the ASP's private settings and chosen actions (diffusion steps). We formulate this as …

Abrupt transitions in the optimization of diffusion with distributed resetting
Pedro Juli\'an-Salgado, Leonardo Dagdug, Denis Boyer
https://arxiv.org/abs/2507.14483

Abrupt transitions in the optimization of diffusion with distributed resetting
Brownian diffusion subject to stochastic resetting to a fixed position has been widely studied for applications to random search processes. In an unbounded domain, the mean first passage time at a target site can be minimized for a convenient choice of the resetting rate. Here we study this optimization problem in one dimension when resetting occurs to random positions, chosen from a distribution with compact support that does not include the target. Depending on the shape of this distribution,…

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
Bowen Zhang, Sicheng Xu, Chuxin Wang, Jiaolong Yang, Feng Zhao, Dong Chen, Baining Guo
https://arxiv.org/abs/2507.23785

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
In this paper, we present a novel framework for video-to-4D generation that creates high-quality dynamic 3D content from single video inputs. Direct 4D diffusion modeling is extremely challenging due to costly data construction and the high-dimensional nature of jointly representing 3D shape, appearance, and motion. We address these challenges by introducing a Direct 4DMesh-to-GS Variation Field VAE that directly encodes canonical Gaussian Splats (GS) and their temporal variations from 3D anima…

Diffusive behavior of transport noise on $\mathbb{S}^2$
Sagy Ephrati, Erik Jansson, Andrea Papini
https://arxiv.org/abs/2508.02707 https://arxiv.org/pdf/25…

Diffusive behavior of transport noise on $\mathbb{S}^2$
We investigate transport theoretically and numerically noise-induced diffusion in flows on the sphere. Previous analysis on the torus demonstrated that suitably chosen transport noise in the Euler equations leads to diffusive behavior resembling the Navier--Stokes equations. Here, we analyze dynamics on the sphere with noise-induced differential elliptic operator dissipation and characterize their energy and enstrophy decay properties. Through structure-preserving numerical simulations with the…