Artificial Intelligence Medical Compendium

Dementia affects millions of older adults worldwide, yet early detection remains difficult outside clinical settings. Traditional models primarily rely on text or voice-based responses, capturing only a limited view of human cognition despite the inh... read more 

Occupancy predictors rely on large persistent banks of Gaussians or learned queries whose size is fixed by hand. Common pruning proxies, such as opacity, activation frequency, or parameter magnitude, do not measure whether removing a row changes the ... read more 

Compositional structure is pervasive in nature and across scales: atoms combine into molecules, molecules into cells, and cells into organisms, while further compositional hierarchies appear within each level. More broadly, compositionality, the reus... read more 

Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation failures. We present VELD-QA, a large-scale benchmark f... read more 

Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data. However, this paradigm introduces a fundamental bottleneck: aligned multimodal datasets are expensive to curate, diffi... read more 

Generative modeling across related distributions raises a question: how can shared structure support accurate generation for a target distribution with limited observations? We develop a statistical framework for diffusion transfer that analyzes a sh... read more 

Diffusion models are notoriously expensive to train, requiring large-scale datasets to learn how to gradually reverse the noise from images over multiple small denoising steps. Current approaches focus on distilling the number of diffusion steps, neg... read more 

Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation strategies may produce varied downstream model behavior, especially for tail concepts supported b... read more 

Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored. Solving this problem would enable long-term behavioral analysis, veterinary monitoring, and animal welfare monitoring by attributing vocalizations... read more 

When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems it most needs to learn. The failed reasoning can nevertheless suggest what to t... read more