Related papers: modAL: A modular active learning framework for Pyt…

Modern time series analysis demands frameworks that are flexible, efficient, and extensible. However, many existing Python libraries exhibit limitations in modularity and in their native support for irregular, multi-source, or sparse data.…

This work presents a modular, Python-based simulator that simplifies the evaluation of novel vehicle control and coordination algorithms in complex traffic scenarios while keeping the implementation overhead low. It allows researchers to…

relentless is an open-source Python package that enables the optimization of objective functions computed using molecular dynamics simulations. It has a high-level, extensible interface for model parametrization; setting up, running, and…

In machine learning (ML), Python serves as a convenient abstraction for working with key libraries such as PyTorch, scikit-learn, and others. Unlike DBMS, however, Python applications may lose important data, such as trained models and…

Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce…

Complex optical design is hindered by conventional piecewise setup, which prevents modularization and therefore abstraction of subsystems at the circuit level. This limits multiple fields that require complex optics systems, including…

We present Any-Modality Augmented Language Model (AnyMAL), a unified model that reasons over diverse input modality signals (i.e. text, image, video, audio, IMU motion sensor), and generates textual responses. AnyMAL inherits the powerful…

rigidPy is a Python package that provides a set of tools necessary for studying rigidity and mechanical response in spring networks. It also includes suitable modules for generating new realizations of networks with applications in glassy…

Active Learning (AL) is a machine learning technique where the model selectively queries the most informative data points for labeling by human experts. Integrating AL with crowdsourcing leverages crowd diversity to enhance data labeling…

Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other…

Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant…

We describe a novel, interdisciplinary, computational methods course that uses Python and associated numerical and visualization libraries to enable students to implement simulations for a number of different course modules. Problems in…

In this paper, we present a new Python library called mPyPl, which is intended to simplify complex data processing tasks using functional approach. This library defines operations on lazy data streams of named dictionaries represented as…

Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete space of module compositions is challenging, especially…

Qudi is a general, modular, multi-operating system suite written in Python 3 for controlling laboratory experiments. It provides a structured environment by separating functionality into hardware abstraction, experiment logic and user…

Polymers are attractive in applications like flexible electronics and thermal interface materials due to their mechanical compliance and processability. However, conventional polymers have low thermal conductivity (TC), limiting their heat…

Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emphasizes deep learning solutions, which are more adept at…

CORL is an open-source library that provides thoroughly benchmarked single-file implementations of both deep offline and offline-to-online reinforcement learning algorithms. It emphasizes a simple developing experience with a…

The Core Imaging Library (CIL) is an open-source versatile Python framework for solving inverse problems with special emphasis on imaging applications such as computed tomography (CT), using a plug-in architecture for data and operators,…

Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era of artificial intelligence. Unlike traditional approaches that require labeled samples for training, AL iteratively selects unlabeled samples…