Related papers: Non-Negative Stiefel Approximating Flow: Orthogona…

Segmenting thin structures like infrastructure cracks and anatomical vessels is a task hampered by topology-sensitive geometry, high annotation costs, and poor generalization across domains. Existing methods address these challenges in…

Normalizing Flows (NF) are Generative models which transform a simple prior distribution into the desired target. They however require the design of an invertible mapping whose Jacobian determinant has to be computable. Recently introduced,…

Deep generative models have recently garnered significant attention across various fields, from physics to chemistry, where sampling from unnormalized Boltzmann-like distributions represents a fundamental challenge. In particular,…

Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based…

Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and pedestrian dynamics. Machine learning has become an invaluable tool for scaling physics-based…

We introduce the Flow Stochastic Segmentation Network (Flow-SSN), a generative segmentation model family featuring discrete-time autoregressive and modern continuous-time flow variants. We prove fundamental limitations of the low-rank…

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a…

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family…

We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis. The core of STARFlow is Transformer Autoregressive Flow (TARFlow), which combines the…

Thrombosis in rotary blood pumps arises from complex flow conditions that remain difficult to translate into reliable and interpretable risk predictions using existing computational models. This limitation reflects an incomplete…

Deep learning models such as CNNs have surpassed human performance in computer vision tasks such as image classification. However, despite their sophistication, these models lack interpretability which can lead to biased outcomes reflecting…

Modeling stochastic dynamics from discrete observations is a key interdisciplinary challenge. Existing methods often fail to estimate the continuous evolution of probability densities from trajectories or face the curse of dimensionality.…

Low-resolution image representation is a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various…

Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoising, typically 10 ODE steps, introduces substantial…

Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of…

Molecular structure elucidation is a fundamental step in understanding chemical phenomena, with applications in identifying molecules in natural products, lab syntheses, forensic samples, and the interstellar medium. We consider the task of…

Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on…

Explorative flow visualization allows domain experts to analyze complex flow structures by interactively investigating flow patterns. However, traditional visual interfaces often rely on specialized graphical representations and…

We introduce the Structured Knowledge Accumulation (SKA) framework, which reinterprets entropy as a dynamic, layer-wise measure of knowledge alignment in neural networks. Instead of relying on traditional gradient-based optimization, SKA…

The modified Method of Successive Approximations (MSA) is an iterative scheme for approximating solutions to stochastic control problems in continuous time based on Pontryagin Optimality Principle which, starting with an initial open loop…