Related papers: SequeL: A Continual Learning Library in PyTorch an…

Recent advancements in code completion models have primarily focused on local file contexts. However, these studies do not fully capture the complexity of real-world software development, which often requires the use of rapidly-evolving…

Motivation: The ability to perform operations on encrypted data has a growing number of applications in bioinformatics, with implications for data privacy in health care and biosecurity. The SEAL library is a popular implementation of fully…

The goal of continual learning is to find a model that solves multiple learning tasks which are presented sequentially to the learner. A key challenge in this setting is that the learner may forget how to solve a previous task when learning…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model…

The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices. The dynamic nature of this data, characterized by…

Despite being an open-source operating system pioneered in the early 90s, UNIX based platforms have not been able to garner an overwhelming reception from amateur end users. One of the rationales for under popularity of UNIX based systems…

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Time-series forecasting is central to many scientific and industrial domains, such as energy systems, climate modeling, finance, and retail. While forecasting methods have evolved from classical statistical models to automated, and neural…

sQUlearn introduces a user-friendly, NISQ-ready Python library for quantum machine learning (QML), designed for seamless integration with classical machine learning tools like scikit-learn. The library's dual-layer architecture serves both…

Kernel continual learning by \citet{derakhshani2021kernel} has recently emerged as a strong continual learner due to its non-parametric ability to tackle task interference and catastrophic forgetting. Unfortunately its success comes at the…

The CERN LHC experiments have begun the LHC Computing Grid project in 2001. One of the project's aims is to develop common software infrastructure based on a development vision shared by the participating experiments. The SEAL project will…

Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…

We introduce rLLM (relationLLM), a PyTorch library designed for Relational Table Learning (RTL) with Large Language Models (LLMs). The core idea is to decompose state-of-the-art Graph Neural Networks, LLMs, and Table Neural Networks into…

Continual learning is a machine learning sub-field specialized in settings with non-iid data. Hence, the training data distribution is not static and drifts through time. Those drifts might cause interferences in the trained model and…

Modern deep learning systems like PyTorch and Tensorflow are able to train enormous models with billions (or trillions) of parameters on a distributed infrastructure. These systems require that the internal nodes have the same memory…

Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several…

PyTorch Adapt is a library for domain adaptation, a type of machine learning algorithm that re-purposes existing models to work in new domains. It is a fully-featured toolkit, allowing users to create a complete train/test pipeline in a few…

Neural networks are the backbone of modern artificial intelligence, but designing, evaluating, and comparing them remains labor-intensive. While numerous datasets exist for training, there are few standardized collections of the models…

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…