Artificial Intelligence Medical Compendium

Antibodies can originate from various sources such as animal immunizations, patient material, DNA/RNA libraries and (AI-based) de novo design. Pre-made (e.g. synthetic) DNA libraries have substantial advantages over traditional immunization campaigns... read more 

Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evaluations at inference. This has motivated extensive research on one-step generative modeling primari... read more 

Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scientific figures, captions, and visual semantics wea... read more 

Feed-forward Gaussian reconstruction builds 3D scenes directly from input images for novel view rendering, but learning Gaussian attributes from predicted geometry for high-quality rendering under large viewpoint changes remains challenging. We analy... read more 

Agents for mixed-degradation image restoration typically learn what a tool does to an image only after running it: failed calls waste computation and harmful outputs go unnoticed until too late. We propose PreActIR, an agentic restoration framework t... read more 

With the rapid development of vision-language models (VLMs), Web-GUI agents have achieved promising performance in interacting with real-world interfaces through screenshot-based grounding. However, high-resolution screenshots and multi-turn historie... read more 

To reach top accuracy, current fully supervised instance segmentation methods severely rely on large-scale pixel-wise labeled datasets. They are usually expensive and time-consuming to obtain. Though weakly or semi-supervised methods utilize cheap bo... read more 

Foundation models have shown strong generalization across scientific domains, but their use in power systems remains largely task-specific. We investigate whether a pretrained tabular foundation model (TFM), TabPFN, can serve as a general-purpose neu... read more 

Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem using only information available before each decision. At each decision th... read more 

Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is unclear how much patient-specific information these representations retain. We investigate this questio... read more