Related papers: Overconfident Oracles: Limitations of In Silico Se…

Driven by advancements in high-throughput biological technologies and the growing number of sequenced genomes, the construction of in silico models at the genome scale has provided powerful tools to investigate a vast array of biological…

Adequate read filtering is critical when processing high-throughput data in marker-gene-based studies. Sequencing errors can cause the mis-clustering of otherwise similar reads, artificially increasing the number of retrieved Operational…

Machine learning (ML) needs industry-standard performance benchmarks to support design and competitive evaluation of the many emerging software and hardware solutions for ML. But ML training presents three unique benchmarking challenges…

Large language models (LLMs) show significant potential in healthcare, prompting numerous benchmarks to evaluate their capabilities. However, concerns persist regarding the reliability of these benchmarks, which often lack clinical…

Time Series Classification (TSC) covers the supervised learning problem where input data is provided in the form of series of values observed through repeated measurements over time, and whose objective is to predict the category to which…

In machine learning contests such as the ImageNet Large Scale Visual Recognition Challenge and the KDD Cup, contestants can submit candidate solutions and receive from an oracle (typically the organizers of the competition) the accuracy of…

The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all real-world applications and scenarios. Apart from high efficiency…

This work addresses the problem of exact schedulability assessment in uniprocessor mixed-criticality real-time systems with sporadic task sets. We model the problem by means of a finite automaton that has to be explored in order to check…

We consider the basic problem of querying an expert oracle for labeling a dataset in machine learning. This is typically an expensive and time consuming process and therefore, we seek ways to do so efficiently. The conventional approach…

The remarkable capability of large language models (LLMs) for in-context learning (ICL) needs to be activated by demonstration examples. Prior work has extensively explored the selection of examples for ICL, predominantly following the…

We introduce seqBench, a parametrized benchmark for probing sequential reasoning limits in Large Language Models (LLMs) through precise, multi-dimensional control over several key complexity dimensions. seqBench allows systematic variation…

Process capability indices such as $C_{pk}$ are widely used for manufacturing decisions, yet are typically applied via deterministic thresholding of finite-sample estimates, ignoring uncertainty and leading to unstable outcomes near the…

Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that researchers are hard-pressed to analyze and study them. The complicated procedures for evaluating innovations, along with the lack of…

Context: Dynamic production environments make it challenging to maintain reliable machine learning (ML) systems. Runtime issues, such as changes in data patterns or operating contexts, that degrade model performance are a common occurrence…

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in…

Hit identification is a critical yet resource-intensive step in the drug discovery pipeline, traditionally relying on high-throughput screening of large compound libraries. Despite advancements in virtual screening, these methods remain…

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature…

Self-supervised learning (SSL) has emerged as a promising paradigm in medical imaging, addressing the chronic challenge of limited labeled data in healthcare settings. While SSL has shown impressive results, existing studies in the medical…

Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate…