Related papers: Performance of an open-source image-based history …
Flow Matching (FM) is a recent framework for generative modeling that has achieved state-of-the-art performance across various domains, including image, video, audio, speech, and biological structures. This guide offers a comprehensive and…
Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based distillation, this type of method typically depends on heuristic guidance…
Denoising Diffusion Probabilistic Models (DDPMs) have established a new state-of-the-art in generative image synthesis, yet their deployment is hindered by significant computational overhead during inference, often requiring up to 1,000…
Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specifications. A common remedy is to project intermediate samples…
District heating (DH) systems play a pivotal role in decarbonizing the building sector's heat supply. While innovative low-exergy DH and cooling systems are increasingly adopted in new developments, the transformation of existing DH systems…
This study investigates the use of High-Performance Computing (HPC) to simulate flow and transport in ultra-large micro-CT images of porous materials using Computational Fluid Dynamics (CFD). Two distinct rock samples, representative of two…
Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each training sample supervises only a single trajectory and…
Current state-of-the-art flow methods are mostly based on dense all-pairs cost volumes. However, as image resolution increases, the computational and spatial complexity of constructing these cost volumes grows at a quartic rate, making…
Recent advances in cross-modal few-shot adaptation treat visual-semantic alignment as a continuous feature transport problem via Flow Matching (FM). However, we argue that Euclidean-based FM overlooks fundamental limitations of flat…
Gromov-Wasserstein (GW) is a powerful tool to compare probability measures whose supports are in different metric spaces. GW suffers however from a computational drawback since it requires to solve a complex non-convex quadratic program. We…
HPC-based applications often have complex workflows with many software dependencies that hinder their portability on contemporary HPC architectures. In addition, these applications often require extraordinary efforts to deploy and execute…
Collecting flow records is a common practice of network operators and researchers for monitoring, diagnosing and understanding a network. Traditional tools like NetFlow face great challenges when both the speed and the complexity of the…
Modeling the evolution of high-dimensional systems from limited snapshot observations at irregular time points poses a significant challenge in quantitative biology and related fields. Traditional approaches often rely on dimensionality…
Recent advances in optical flow estimation have prioritized accuracy at the cost of growing GPU memory consumption, particularly for high-resolution (FullHD) inputs. We introduce MEMFOF, a memory-efficient multi-frame optical flow method…
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time…
We present a computational framework to address the flow of two immiscible viscous liquids which co-flow into a shallow rectangular container at one side, and flow out into a holding container at the opposite side. Assumptions based on the…
Quantitative monitoring of subsurface changes is essential for ensuring the safety of geological CO2 sequestration. Full-waveform monitoring (FWM) can resolve these changes at high spatial resolution, but conventional deterministic…
To track rapid changes within our water sector, Global Water Models (GWMs) need to realistically represent hydrologic systems' response patterns - such as baseflow fraction - but are hindered by their limited ability to learn from data.…
Radio astronomy observatories with high throughput back end instruments require real-time data processing. While computing hardware continues to advance rapidly, development of real-time processing pipelines remains difficult and…
Direct pore scale simulations of two-fluid flow on digital rock images provide a promising tool to understand the role of surface wetting phenomena on flow and transport in geologic reservoirs. We present computational protocols that mimic…