Related papers: Is your data alignable? Principled and interpretab…
The Smatch metric is a popular method for evaluating graph distances, as is necessary, for instance, to assess the performance of semantic graph parsing systems. However, we observe some issues in the metric that jeopardize meaningful…
Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that…
Synthetic Aperture Radar (SAR) and optical imagery provide complementary strengths that constitute the critical foundation for transcending single-modality constraints and facilitating cross-modal collaborative processing and intelligent…
Cellular signaling is essential in information processing and decision making. Therefore, a variety of experimental approaches have been developed to study signaling on bulk and single-cell level. Single-cell measurements of signaling…
In the rapid development of artificial intelligence, solving complex AI tasks is a crucial technology in intelligent mobile networks. Despite the good performance of specialized AI models in intelligent mobile networks, they are unable to…
High-dimensional multimodal data arises in many scientific fields. The integration of multimodal data becomes challenging when there is no known correspondence between the samples and the features of different datasets. To tackle this…
As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on…
High-throughput technologies such as next generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of…
Aligning protein interaction networks (PPI) of two or more organisms consists of finding a mapping of the nodes (proteins) of the networks that captures important structural and functional associations (similarity). It is a well studied but…
Datasets are growing not just in size but in complexity, creating a demand for rich models and quantification of uncertainty. Bayesian methods are an excellent fit for this demand, but scaling Bayesian inference is a challenge. In response…
Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of…
Network alignment consists of finding a structure-preserving correspondence between the nodes of two correlated, but not necessarily identical, networks. This problem finds applications in a wide variety of fields, from the alignment of…
A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…
Mathematical methods together with measurements of single-cell dynamics provide unprecedented means to reconstruct intracellular processes that are only partly or indirectly accessible experimentally. To obtain reliable reconstructions the…
Artificial Intelligence (AI) holds great promise for transforming healthcare, particularly in disease diagnosis, prognosis, and patient care. The increasing availability of digital medical data, such as images, omics, biosignals, and…
Despite advancements in Computer-Aided Diagnosis (CAD) systems, breast cancer remains one of the leading causes of cancer-related deaths among women worldwide. Recent breakthroughs in Artificial Intelligence (AI) have shown significant…
This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty…
Deep learning-based AI models have been extensively applied in genomics, achieving remarkable success across diverse applications. As these models gain prominence, there exists an urgent need for interpretability methods to establish…
We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference.…