Related papers: Les Houches guide to reusable ML models in LHC ana…

In High Energy Physics (HEP), analysis metadata comes in many forms -- from theoretical cross-sections, to calibration corrections, to details about file processing. Correctly applying metadata is a crucial and often time-consuming step in…

Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML's…

We present an extension of the expert mode of the MadAnalysis 5 program dedicated to the design or reinterpretation of high-energy physics collider analyses. We detail the predefined classes, functions and methods available to the user and…

Given the growing amount of industrial data spaces worldwide, deep learning solutions have become popular for predictive maintenance, which monitor assets to optimise maintenance tasks. Choosing the most suitable architecture for each…

In this work we demonstrate that significant gains in performance and data efficiency can be achieved in High Energy Physics (HEP) by moving beyond the standard paradigm of sequential optimization or reconstruction and analysis components.…

Hybrid intelligence aims to enhance decision-making, problem-solving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial intelligence. With the rise of Large Language Models (LLM),…

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

In the last decade, the use of Machine and Deep Learning (MDL) methods in Condensed Matter physics has seen a steep increase in the number of problems tackled and methods employed. A number of distinct MDL approaches have been employed in…

The TREC Deep Learning (DL) Track studies ad hoc search in the large data regime, meaning that a large set of human-labeled training data is available. Results so far indicate that the best models with large data may be deep neural…

Les Houches activities in 2021 were truncated due to the lack of an in-person component. However, given the rapid progress in the field, and the restart of the LHC, we wanted to continue the bi-yearly tradition of updating the standard…

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such…

Deep decarbonization of the energy sector will require massive penetration of stochastic renewable energy resources and an enormous amount of grid asset coordination; this represents a challenging paradigm for the power system operators who…

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing…

High-throughput data generation methods and machine learning (ML) algorithms have given rise to a new era of computational materials science by learning relationships among composition, structure, and properties and by exploiting such…

As they become more capable, large language models (LLMs) have continued to rapidly increase in size. This has exacerbated the difficulty in running state of the art LLMs on small, edge devices. Standard techniques advocate solving this…

Reproducibility should be a cornerstone of scientific research and is a growing concern among the scientific community and the public. Understanding how to design services and tools that support documentation, preservation and sharing is…

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces…

In this paper, we propose a method to perform empirical analysis of the loss landscape of machine learning (ML) models. The method is applied to two ML models for scientific sensing, which necessitates quantization to be deployed and are…