Artificial Intelligence Medical Compendium

Domain adaptive object detection (DAOD) aims to reduce performance degradation due to distribution shifts between training (source) and testing (target) datasets. However, owing to insufficient modeling of fine-grained features and limited instance-l... read more 

Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles or divergence. This paper investigates these instabilities through the lens of continuous-time dyna... read more 

We consider online binary prediction with paid stochastic features, where the learner can spend resources to obtain better observations of the underlying features. This setting is motivated by applications such as medical testing, where additional co... read more 

We study dictionary learning for probability measure-valued data by embedding measures into Hilbert spaces using features derived from optimal transport geometry. We learn data-adapted dictionaries through sparse autoencoder parameterizations, produc... read more 

Image deblurring is a fundamental task in computer vision, yet existing methods mainly specialize in isolated scenarios. Consequently, the deblurring performance of these models drops significantly across scenarios with different cameras and image co... read more 

Vision-language models (VLMs) learn strong statistical regularities during training, which can make them fail to properly respond to visual evidence when input images violate those regularities. It is challenging to disambiguate these prior-induced e... read more 

Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of-the-art (SOTA) removal attacks can suppress embedded signals with little perceptual degradation. This vulnerability limits the ef... read more 

Visual representations are largely developed for understanding, yet what makes them useful for generation remains unclear. We study this question in pixel diffusion transformers and uncover two key insights. First, better representation quality does ... read more 

Natural-image-pretrained foundation models are increasingly adapted to medical imaging, yet transfer remains unreliable under domain shift, modality heterogeneity, and label scarcity. We trace part of this fragility to an overlooked design choice. St... read more 

Softmax-based multimodal emotion recognition methods often assign high confidence even when sensor data are corrupted or contradictory, for example when facial expressions suggest positive valence while vocal prosody indicates negative arousal. We pr... read more