Latest AI and machine learning research in ophthalmology for healthcare professionals.
Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes domains such as medicine. Traditional approaches primarily rely on probability outputs from trained models (point predictions), which provide no formal guarantees on prediction coverage and often require additional calibra- tion techniques to improve reliability. In contrast, conformal prediction (r...
Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but lack visual grounding. Recent training-free detectors use internal signals such as token likelihood, attention, visual confidence, or image-text similarity to identify hallucinated objects. These signals are useful, but they are often source-confounde...
Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to d...
Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution image...
Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content i...
Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodolog...
Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning...
Patient identity errors can compromise longitudinal medical records, research databases, and downstream clinical decisions. We present a retinal biome...
Surface material recognition from incomplete visual observations remains a challenging problem in robotic perception and environmental understanding. ...
Attributing an artwork to an artist has traditionally relied on detailed visual observations and descriptions, known as stylistic analysis in art hist...
Large Vision-Language Models (LVLMs) achieve strong performance across many multimodal tasks; however, they often exploit spurious object-background c...
Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for sce...
Diabetic retinopathy (DR) is a major cause of preventable blindness, creating a need for accurate and trustworthy automated screening. This study inve...
Multimodal large language models (MLLMs) can memorize identity-specific facts about people in their fine-tuning data, creating privacy risks when a pe...
Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated la...
Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ...
Which visual choices make a post perform better? A growing literature answers this question with pooled coefficients estimated across many creators, w...
With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitig...
Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ...
Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing i...