Latest AI and machine learning research in alternative medicine for healthcare professionals.
Reliable deployment of multimodal large language models (MLLMs) requires deciding whether a confident visual answer should be trusted, reviewed, or routed to a stronger system. Confidence scores capture candidate margins, but not where the estimated signed visual readouts associated with those margins come from or how they are distributed. We study inference-time risk detection for closed visual a...
High-resolution visual question answering (HR-VQA) is often treated as a problem of insufficient evidence acquisition, where failing multimodal large language models must inspect images again through cropping, re-encoding, or multi-round search. We show that this view is incomplete: in many cases, fine-grained evidence has already survived visual encoding and become identifiable and influential wi...
Vision-language models (VLMs), such as CLIP, are vulnerable to adversarial attacks, posing a serious problem for real-life applications and deployment...
Vision models do not form a representation at once; each block revises it. We ask whether the resulting computation path contains evidence that the fi...
The promise of multimodal fusion lies in combining complementary sources of evidence, yet more evidence does not always yield a better prediction. Rec...
Background: Regurgitant valvular heart disease (rVHD) is a major cause of cardiovascular morbidity. Echocardiography is the diagnostic standard but is...
Vision models do not form a representation at once; each block revises it. We ask whether the resulting computation path contains evidence that the fi...
Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model mus...
Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. H...
Medical world models offer a framework for extending medical artificial intelligence beyond static prediction by representing evolving patient states ...
Unmanned aerial vehicle (UAV)-satellite cross-view geo-localization matches UAV images against satellite imagery and has achieved impressive accuracy ...
Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under do...
Sentimental Image Captioning (SIC) requires balancing emotional expression with visual fidelity. Existing methods often struggle with this trade-off, ...
Phenotype-driven diagnostic benchmarks usually report the rank of the reference disease, but they rarely reveal which plausible alternatives are ranke...
Diagnosing the root cause of anomalies is essential for safe industrial operation. Despite extensive sensor instrumentation, formulating hypotheses an...
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbone...
Long-document multimodal question answering requires more than retrieving relevant chunks from a large document. Different queries require different e...
Infrared small target detection (ISTD) remains challenging because tiny, low-contrast targets are easily overwhelmed by clutter, noise, or occlusion. ...
PairUAV relative localization maps two UAV images to a polar navigation command. Although heading and range share the same pairwise pose context, trea...
Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmar...