Artificial Intelligence Medical Compendium

Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal preference data remains largely unexplored. Existing preference poisoning attacks either corrupt expl... read more 

Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions. Within this view, supervised fine-tuning (SFT) is shown to induce dense updates that perturb the ... read more 

Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, th... read more 

Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reused as a prior and combined with a task-specific likelihood to sample from the corresponding posteri... read more 

A patient's pathology case spans tens of slides from distinct specimens and anatomical sites, each carrying non-redundant, site-specific evidence. Forming a patient-level conclusion therefore requires locating the slides relevant to a given question ... read more 

Deep learning has enabled substantial advances in oncology, including cancer detection and diagnosis, medical image analysis, tumor characterization, treatment planning, response assessment, and outcome prediction. However, conventional data-driven m... read more 

Agentic visual generation produces experience that can improve the native understanding (agent) and generation roles of a unified multimodal backbone, but task success alone does not determine which role should learn. Generator updates can also make ... read more 

Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be summarized coarsely, while object boundaries and literal text require ... read more 

This paper extends the non-unique games framework introduced in Bandeira et al. (2020) to address symmetric structures. Precisely, we consider the problem \[ \begin{aligned} \underset{g_1,\ldots,g_n\in \mathcal{G}}{\operatorname{min}}\,\, \frac{1}{... read more 

Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models recover this structure from RGB, but existing methods either fuse the estimated features with visual ... read more