相关论文: CapyMOA: Efficient Machine Learning for Data Strea…

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently…

Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their…

Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains…

We present an overview of Sherpa, an open source Python project, and discuss its development history, broad design concepts and capabilities. Sherpa contains powerful tools for combining parametric models into complex expressions that can…

Continual learning enables the incremental training of machine learning models on non-stationary data streams.While academic interest in the topic is high, there is little indication of the use of state-of-the-art continual learning…

We present DataFlow, a computational framework for building, testing, and deploying high-performance machine learning systems on unbounded time-series data. Traditional data science workflows assume finite datasets and require substantial…

Most of the learning-based algorithms for bitrate adaptation are limited to offline learning, which inevitably suffers from the simulation-to-reality gap. Online learning can better adapt to dynamic real-time communication scenes but still…

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…

This report presents the test results Python library BaumEvA, which implements evolutionary algorithms for optimizing various types of problems, including computer vision tasks accompanied by the search for optimal model architectures.…

Limbo is an open-source C++11 library for Bayesian optimization which is designed to be both highly flexible and very fast. It can be used to optimize functions for which the gradient is unknown, evaluations are expensive, and runtime cost…

Predictive process monitoring (PPM) focuses on predicting future process trajectories, including next activity predictions. This is crucial in dynamic environments where processes change or face uncertainty. However, current frameworks…

Currently, Python is one of the most widely used languages in various application areas. However, it has limitations when it comes to optimizing and parallelizing applications due to the nature of its official CPython interpreter,…

Complexity analysis offers assurance of program's runtime behavior, but large classes of programs remain unanalyzable by existing automated techniques.The mwp-flow analysis sidesteps many difficulties shared by existing approaches, and…

Active learning, a powerful paradigm in machine learning, aims at reducing labeling costs by selecting the most informative samples from an unlabeled dataset. However, the traditional active learning process often demands extensive…

Understanding how the brain functions is one of the biggest challenges of our time. The analysis of experimentally recorded neural firing patterns (spike trains) plays a crucial role in addressing this problem. Here, the PySpike library is…

AI has led to significant advancements in computer vision and image processing tasks, enabling a wide range of applications in real-life scenarios, from autonomous vehicles to medical imaging. Many of those applications require efficient…

Exploiting knowledge about the structure of a problem can greatly benefit the efficiency and scalability of an Evolutionary Algorithm (EA). Model-Based EAs (MBEAs) are capable of doing this by explicitly modeling the problem structure. The…

Training large foundation models costs hundreds of millions of dollars, making deployment optimization critical. Current approaches require machine learning engineers to manually craft training recipes through error-prone trial-and-error on…

With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research, we focus on two features of DGMs: (1) deep neural networks…