Related papers: Safer Together: Machine Learning Models Trained on…

Machine learning is traditionally studied at the model level: researchers measure and improve the accuracy, robustness, bias, efficiency, and other dimensions of specific models. In practice, the societal impact of machine learning is…

Typical design flows are hierarchical and rely on assembling many individual technology elements from standard cells to complete boards. Providers use compact models to provide simplified views of their products to their users. Designers…

We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize…

Brain stroke remains one of the principal causes of death and disability worldwide, yet most tabular-data prediction models still hover below the 95% accuracy threshold, limiting real-world utility. Addressing this gap, the present work…

As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not encountered during training -- has garnered significant…

Probability forecasting is common in the geosciences, the finance sector, and elsewhere. It is sometimes the case that one has multiple probability-forecasts for the same target. How is the information in these multiple forecast systems…

Predicting risk map of traffic accidents is vital for accident prevention and early planning of emergency response. Here, the challenge lies in the multimodal nature of urban big data. We propose a compact neural ensemble model to alleviate…

How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications. However, a model trained on a naive merge of different datasets tends to…

ML models deployed in production often have to face unknown domain changes, fundamentally different from their training settings. Performance prediction models carry out the crucial task of measuring the impact of these changes on model…

This study examines the generalization ability of algorithm performance prediction models across various benchmark suites. Comparing the statistical similarity between the problem collections with the accuracy of performance prediction…

Loss reserving generally focuses on identifying a single model that can generate superior predictive performance. However, different loss reserving models specialise in capturing different aspects of loss data. This is recognised in…

Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its generalization abilities to new tasks are questionable. We ask…

Creating models from past observations and ensuring their effectiveness on new data is the essence of machine learning. However, selecting models that generalize well remains a challenging task. Related to this topic, the Rashomon Effect…

Traffic simulators are widely used to study the operational efficiency of road infrastructure, but their rule-based approach limits their ability to mimic real-world driving behavior. Traffic intersections are critical components of the…

Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical…

Generating representative rear-end crash scenarios is crucial for safety assessments of Advanced Driver Assistance Systems (ADAS) and Automated Driving systems (ADS). However, existing methods for scenario generation face challenges such as…

Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-computation. Despite empirical successes, a unified theory for…

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Automated cyber threat detection in computer networks is a major challenge in cybersecurity. The cyber domain has inherent challenges that make traditional machine learning techniques problematic, specifically the need to learn continually…

Traffic microscopic simulation applications are a common tool in road transportation analysis and several attempts to perform road safety assessments have recently been carried out. However, these approaches often ignore causal…