Artificial Intelligence Medical Compendium

Adapting a single vision-language model to medical image parsing requires training choices that reflect the demands of each task. We study task-specific adaptation with Qwen3.5-9B for FLARE 2026 Task 3, covering six task families and seven imaging mo... read more 

Plant-based cheeses often fail to reproduce the texture of dairy cheese. Closing this gap is slow because the reference methods, texture profile analysis (TPA) and sensory panels, destroy the sample and are poorly suited to screening many formulation... read more 

Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tracker, inherited from SAM 2, stores information from past frames in a memory bank, managed by a si... read more 

This work presents a compact and reproducible pipeline for synthesizing and curating image-based instruction-response pairs for DCVLR. We draw from the Cauldron collection and use Magpie-style instruction and response synthesis with Qwen2.5-VL-7B Ins... read more 

Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their stealthiness remains inconsistently defined and measured. Existing work often studies only one observable aspect of stealthiness, su... read more 

Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still score answer endpoints alone. Such scoring conflates memorized facts with stepwise derivation, tre... read more 

The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses serious privacy risks: a passive adversary with black-box LVLM access can infer a user's location from... read more 

Accurate nuclei segmentation underpins quantitative computational pathology, yet remains challenging due to morphological variability, weak boundaries, nuclear crowding, and pronounced domain shifts arising from differences in tissue preparation, sta... read more 

Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persistence of object identities and abrupt changes in relationships. Existing methods aggregate informati... read more 

Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GPU accelerators, or where that energy goes. We measure total-system energy, latency, and thermal be... read more