Artificial Intelligence Medical Compendium

Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual grounding, external retrieval, and fact composition. A key challenge is to preserve the dependencies linking localized visual anchor... read more 

Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-guided gener... read more 

We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation models, with or without depth priors. In contrast to previous approaches that normally evaluate depth... read more 

Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been produced. A model must determine the next action from its generated st... read more 

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action follow... read more 

Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output... read more 

Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sensor measured it, so measurement differences travel with the representation into new cohorts. We as... read more 

Generative creative interfaces routinely report the user's position within a space of possibilities. Such displays imply that the quantities shown were measured from the artefact; in a growing class of systems they are instead predicted by a language... read more 

Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, af... read more 

Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the im... read more