Artificial Intelligence Medical Compendium

Zero-shot Chinese character recognition (ZS-CCR) aims to recognize characters whose categories are never observed during training, and typically relies on the compositional structure shared between seen and unseen characters. Recent CLIP-style method... read more 

Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim along both routes to a pixel-space backbone. We pretrain Iris-3B, a 3B-parameter ... read more 

This paper addresses the prediction of adjacency between pairs of 2D fragments based on their contours. We improved the two-stage architecture proposed in Beaulac's thesis, in which a rotation-equivariant Siamese convolutional neural network scores p... read more 

Referring Expression Segmentation (RES) links natural-language descriptions to pixel-level object masks. Yet standard evaluation provides limited insight into instance-level referential reasoning: it does not systematically distinguish referential lo... read more 

Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \textbf{SpatialUQ}, a post-hoc uncertainty method using only output probabilities. It measures th... read more 

Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with real-time efficiency remains challenging. Beyond vocabulary scaling, zero-shot generalization may ... read more 

Aerial object detection faces substantial scale and density variations. Small objects are easily degraded by downsampling and feature compression, while medium and large objects require sufficient global context. Existing methods mainly follow two pa... read more 

Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that separates visual state transition learning from dense video generation. We construct event-aligned... read more 

Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describing danger indicates the hazard itself. Yet policy return and collision rate cannot reveal whether a sc... read more 

Real-world applications require 6D pose estimation to be accurate, fast, and scalable to unseen objects. This paper introduces WAPR, a zero-shot wide-angle pose refinement model that refines candidate poses with rotational deviations up to 90 degrees... read more