This paper establishes a connection between neural network approximation of score functions and approximation of probability distributions generated by reverse diffusion models.

This paper investigates the application of transformer-based diffusion models for simulating and reconstructing hydrological time series using data from six sites in North-East France.

This paper introduces DiPhon, a diffusion framework for size-scalable graph generation, using a continuous diffusion process on the graphon space and a discretized graph-level process.

The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…

The paper introduces Strong Stochastic Flow Maps (SSFMs), a novel framework that directly learns the strong solution map of additive-noise Stochastic Differential Equations (SDEs), enabling few-step s…

The Parameterized Diffusion Policy (PDP) framework transforms diffusion models from general stochastic generators into precise, steerable tools for learning and adapting complex robotic behaviors by e…

This paper investigates the transparency of DiffusionGemma, a model with a larger fraction of computation in a continuous latent space, and shows that it can be made more transparent by mapping inform…

This paper shows that small forward-marginal error in score matching does not guarantee numerical stability, and constructs a smooth score field with small forward-marginal error but diverging moments…

This paper derives the Oracle Distance theorem for discrete diffusion models and proves that the negative ELBO is equal to the data entropy plus the path KL from the oracle reverse process to the lear…

The paper introduces residualized temporal Sparse Autoencoders (SAEs) to analyze the full spatiotemporal structure of activations generated during the iterative denoising process of diffusion models,…

This paper develops a perturbation theory for spherical Hellinger-Kantorovich (SHK) gradient flows, providing explicit, time-dependent bounds on divergence metrics to guarantee differential privacy fo…

The paper shows that the scaled overshoot of a minimum value in a Gaussian process converges to an exponential random variable as the minimum value increases, and identifies the limiting measure as an…

This paper develops a novel, computationally efficient method to quantify the uncertainty in wide neural network predictions by characterizing the limiting random fluctuations using stochastic evoluti…

This paper resolves the finite-signed uniqueness problem for a multidimensional reflected diffusion using pathwise differentiability and feasible directional differentiability.

The paper introduces SARDI, a novel, training-free framework that uses low-confidence 'lookahead' tokens generated during the denoising process of discrete diffusion language models to dynamically gui…

Introduce Deep Second-Order Stochastic Residual Method (D2SRM) for high-dimensional, Hessian-dependent fully nonlinear parabolic PDEs, establish well-posedness, and develop population-level convergenc…