Artificial Intelligence Medical Compendium

Frozen features of brain MRI foundation models lose accuracy on new datasets, a failure usually blamed on the features encoding where each scan came from. We show that the failure lies elsewhere. Across 17 public datasets and eight frozen representat... read more 

Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly. Redundancy arises both from repeated observations of the same scene regions acro... read more 

Recent image-to-3D models generate complete, high-quality assets from a single image, with global shape and appearance that are already convincing; what remains is the fine scale, where small, thin, elongated, or detail-rich regions are reconstructed... read more 

Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32 send 99.7% of triggered source-class images to the attacker's class. The usual defenses look for the poison inside a model traine... read more 

Recent advances in large-scale foundation models have enabled strong generalization across a wide range of clinical and research tasks in magnetic resonance imaging (MRI). However, existing vision-language MRI models remain limited in anatomy-specifi... read more 

Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by that change. When asked what would have happened if a doctor had not recommended surgery, the model ou... read more 

The optimization objective for e-commerce advertising creatives has shifted from aesthetic quality to online business metrics like click-through rate (CTR). Recent methods generate appealing ad images from product images by constructing CTR-based rew... read more 

Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size memory must retain many associations, connect information across positions, and preserve relevant structure without being overwhelme... read more 

Generative MRI reconstruction maps an initial source distribution to the target image distribution along a learned recovery trajectory. Common generative methods, such as diffusion and flow, typically learn fine-grained local dynamics whose integrati... read more 

Attention heads that attend to image regions relevant to a question are increasingly used to steer, ground and interpret vision-language models (VLMs) and to reduce their hallucinations. They are mostly found by ranking heads with an attention- patte... read more