Related papers: Is your data alignable? Principled and interpretab…

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has…

The increasing complexity of AI systems has made understanding their behavior critical. Numerous interpretability methods have been developed to attribute model behavior to three key aspects: input features, training data, and internal…

Finite population inference is a central goal in survey sampling. Probability sampling is the main statistical approach to finite population inference. Challenges arise due to high cost and increasing non-response rates. Data integration…

This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for. We posit…

The integration of AI-assisted biomedical image analysis into clinical practice demands AI-generated findings that are not only accurate but also interpretable to clinicians. However, existing biomedical AI models generally lack the ability…

High-throughput omics profiling advancements have greatly enhanced cancer patient stratification. However, incomplete data in multi-omics integration presents a significant challenge, as traditional methods like sample exclusion or…

Research increasingly relies on computational methods to analyze experimental data and predict molecular properties. Current approaches often require researchers to use a variety of tools for statistical analysis and machine learning,…

High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely…

Hyperspectral imaging (HSI) is an advanced sensing modality that simultaneously captures spatial and spectral information, enabling non-invasive, label-free analysis of material, chemical, and biological properties. This Primer presents a…

Single-cell omics technologies have transformed our understanding of cellular diversity by enabling high-resolution profiling of individual cells. However, the unprecedented scale and heterogeneity of these datasets demand robust frameworks…

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Adaptive interventions (AIs) are increasingly becoming popular in medical and behavioral sciences. An AI is a sequence of individualized intervention options that specify for whom and under what conditions different intervention options…

There is a growing need for pluralistic alignment methods that can steer language models towards individual attributes and preferences. One such method, Self-Supervised Alignment with Mutual Information (SAMI), uses conditional mutual…

General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where…

Current AI-assisted skin image diagnosis has achieved dermatologist-level performance in classifying skin cancer, driven by rapid advancements in deep learning architectures. However, unlike traditional vision tasks, skin images in general…

Specific emitter identification (SEI) distinguishes emitters by utilizing hardware-induced signal imperfections. However, conventional SEI techniques are primarily designed for single-emitter scenarios. This poses a fundamental limitation…

Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream diagnostic tasks. Hematological cytology is unique in that visual single-cell evaluation…

Dermatological conditions affect 1.9 billion people globally, yet accurate diagnosis remains challenging due to limited specialist availability and complex clinical presentations. Family history significantly influences skin disease…

Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misinterpretation. We performed the first large-scale, systematic…

We study high-dimensional two-sample mean comparison and address the curse of dimensionality through data-adaptive projections. Leveraging the low-dimensional and localized signal structures commonly seen in single-cell genomics data, our…