Related papers: DREENA-A framework as a QGP tomography tool

Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We…

A versatile approach to modeling the conformations and energetics of DNA loops is presented. The model is based on the classical theory of elasticity, modified to describe the intrinsic twist and curvature of DNA, the DNA bending…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

Deep learning is a state of the art method for a lot of applications. The main issue is that most of the real-time data is highly imbalanced in nature. In order to avoid bias in training, cost-sensitive approach can be used. In this paper,…

We describe AthenaK: a new implementation of the Athena++ block-based adaptive mesh refinement (AMR) framework using the Kokkos programming model. Finite volume methods for Newtonian, special relativistic (SR), and general relativistic (GR)…

Recent advances in domain adaptation, especially those applied to heterogeneous facial recognition, typically rely upon restrictive Euclidean loss functions (e.g., $L_2$ norm) which perform best when images from two different domains (e.g.,…

This paper presents a new data-driven finite element framework that is applicable to a broad range of engineering simulation problems. In the data-driven approach, the conservation laws and boundary conditions are satisfied by means of the…

We present the first part of an efficient framework for nonlinear beam dynamics, termed Approximate Invariant Analysis (AIA). The framework is based on the construction of approximate invariants~[Y.~Li, D.~Xu, and Y.~Hao, Phys.\ Rev.\…

We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured in novel…

State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where…

Prediction of material properties from first principles is often a computationally expensive task. Recently, artificial neural networks and other machine learning approaches have been successfully employed to obtain accurate models at a low…

A data driven finite element method (DDFEM) that accounts for more than two material state variables has been presented in this work. DDFEM framework is motivated from (1,2) and can account for multiple state variables, viz. stresses,…

In the present work, a generative deep learning framework combining a Co-optimized Variational Autoencoder (Co-VAE) architecture with quantitative structure-property relationship (QSPR) techniques is developed to enable accelerated inverse…

Recently, a new probabilistic "data fusion" framework based on Bayesian principles has been developed on JET and W7-AS. The Bayesian analysis framework folds in uncertainties and inter-dependencies in the diagnostic data and signal…

With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model…

Data-based approaches are promising alternatives to the traditional analytical constitutive models for solid mechanics. Herein, we propose a Gaussian process (GP) based constitutive modeling framework, specifically focusing on planar,…

Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a…

We present TUNA, an open-source quantum chemistry program specifically designed for atoms and diatomic molecules. Within this narrow molecular domain, a broad and consistent set of electronic structure methods and calculation types is…

This paper presents a novel framework to accelerate route prediction in Drone-as-a-Service operations through weather-aware deep learning models. While classical path-planning algorithms, such as A* and Dijkstra, provide optimal solutions,…

Implementation details and test cases of a newly developed hydrodynamic code, AMRA, are presented. The numerical scheme exploits the adaptive mesh refinement technique coupled to modern high-resolution schemes which are suitable for…