Artificial Intelligence Medical Compendium

Myopic vision degrades the quality of human vision due to spherical eye defocus aberrations that impair the perception of fine spatial details. To address this limitation, this work proposes a deep learning-based approach to computationally design tr... read more 

The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neurons. On tasks spanning many domains, it displays emergent thought processes that have not been expla... read more 

Existing illumination estimation methods primarily recover lighting distributions for rendering, but typically leave the contributions of individual physical light sources at specific scene locations implicit. We address this gap by leveraging the sc... read more 

Atmospheric turbulence creates complex spatial and temporal distortions that significantly reduce image quality. This work compares two deep learning methods for turbulence reduction: Generative Adversarial Networks (GANs) and Transformer-based model... read more 

We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite (2B parameters) and Kandinsky S2V 1.0 Pro (21B parameters). From a single reference image, a speec... read more 

One-step diffusion distillation achieves strong performance on small datasets but remains insufficient for high-resolution or complex text-to-image settings. Extending to multistep distillation often requires training data, suffers from early-step de... read more 

Sequential screening policies must use acquired feedback effectively under a fixed experiment budget. We study acquisition-time residual adaptation: a small ranking correction built from fixed historical features and anchored to base scores recorded ... read more 

Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational systems. Yet event logs can differ substantially in their event semantics, label spaces, interaction pa... read more 

Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models also differ in architecture, pretraining objective and data, while downst... read more 

Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it. A false answer presents an unsupported claim as fact; an over-abstention hides what the report says. Yet RadQA results a... read more