Related papers: A data-driven study on Implicit LES using a spectr…

In this review, the methodology of large eddy simulations (LES) is introduced and applications in astrophysics are discussed. As theoretical framework, the scale decomposition of the dynamical equations for compressible neutral fluids by…

Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution. In this paper, we present a robust method for high-quality…

Results of numerical simulations obtained by a staggered finite difference scheme together with an efficient immersed boundary method are presented to understand the effects of the shape of three-dimensional obstacles on the transition of a…

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe…

This paper addresses the problem of data-driven model discrimination for unknown switched systems with unknown linear temporal logic (LTL) specifications, representing tasks, that govern their mode sequences, where only sampled data of the…

We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs).…

This paper addresses a data-driven input reconstruction problem based on Willems' Fundamental Lemma in which unknown input estimators (UIEs) are constructed directly from historical I/O data. Given only output measurements, the inputs are…

We describe a spectrally-filtered discrete-in-time downscaling data assimilation algorithm and prove, in the context of the two-dimensional Navier--Stokes equations, that this algorithm works for a general class of interpolants, such as…

Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training often has to run on-premise under strict data-local…

This study investigates a method to evaluate time-series datasets in terms of the performance of deep neural networks (DNNs) with state space models (deep SSMs) trained on the dataset. SSMs have attracted attention as components inside DNNs…

Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. Their robustness as general approximators has been shown in a wide variety of data…

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

In this work, we consider a Federated Edge Learning (FEEL) system where training data are randomly generated over time at a set of distributed edge devices with long-term energy constraints. Due to limited communication resources and…

One of the key challenges of machine learning (ML) based intrusion detection system (IDS) is the expensive computational complexity which is largely due to redundant, incomplete, and irrelevant features contain in the IDS datasets. To…

The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive…

A resolution-independent data-driven stochastic parametrization method for subgrid-scale processes in coarsened fluid descriptions is proposed. The method enables the inclusion of high-fidelity data into the coarsened flow model, thereby…

Physics-constrained data-driven computing is an emerging hybrid approach that integrates universal physical laws with data-driven models of experimental data for scientific computing. A new data-driven simulation approach coupled with a…

Monte Carlo Tree Search (MCTS) based methods provide promising approaches for generating synthetic data to enhance the self-training of Large Language Model (LLM) based multi-agent systems (MAS). These methods leverage Q-values to estimate…

Many applications such as scientific simulation, sensing, and power grid monitoring tend to generate massive amounts of data, which should be compressed first prior to storage and transmission. These data, mostly comprised of floating-point…

We present a scalable, high-order implicit large-eddy simulation (ILES) approach for incompressible transitional flows. This method employs the mass-conserving mixed stress (MCS) method for discretizing the Navier-Stokes equations. The MCS…