Artificial Intelligence Medical Compendium

Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining. However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundanc... read more 

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design objectives they s... read more 

Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical insomnia and boundary instability in narcolepsy type... read more 

Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpre... read more 

Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviat... read more 

Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilitie... read more 

A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables. Yet even a strong generalist like $π_{0.5}$ achieves 0% pickup success in our captured deployment... read more 

This review article explores the application of artificial intelligence (AI) within Advanced Therapy Medicinal Products (ATMPs) analysis, specifically focusing on challenges related to chemistry, manufacturing, and controls (CMC) and manufacturing pr... read more 

COPD is a progressive and heterogeneous condition characterised by varying combinations of emphysema, small airway disease, chronic bronchitis and exacerbations. Although multiple symptomatic therapies exist, no disease-modifying treatments are avail... read more 

Robotic endoscopy offers a potential route to autonomous gastrointestinal navigation. However, autonomous intestinal navigation is hindered by non-rigid lumen deformation and visual degradation from specular reflections, which compromise accurate per... read more