Latest AI and machine learning research in ophthalmology for healthcare professionals.
Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extending these visual foundations to multi-modal reasoning tasks is severely bottlenecked by the prohibitive cost of expert textual annotations. To overcome this scalability limitation, we introduce \textbf{LIME}, a large-scale multi-modal dataset derived...
Accurate prognostication and risk estimation are essential for guiding clinical decision-making and optimizing patient management. While radiologist-assessed features from CT scans provide valuable indicators of disease severity and outcomes, interpreting such images requires expert knowledge, and translating rich visual information into textual summaries inevitably leads to information loss. In t...
While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs ar...
Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent ...
Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal...
Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images rema...
In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ...
Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, w...
Automating medical reports for retinal images requires a sophisticated blend of visual pattern recognition and deep clinical knowledge. Current Large ...
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-...
Diabetic retinopathy (DR) is a leading cause of vision impairment worldwide, and automated grading systems play a crucial role in large-scale screenin...
Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning t...
Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remot...
Peripheral Blood Smear (PBS) is a critical microscopic examination in hematopathology that yields whole-slide imaging (WSI). Unlike solid tissue patho...
Abstract Background Diabetic Retinopathy (DR) is one of the leading cause of vision loss and blindness. AI models have been instrumental in providing ...
Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most resear...
Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual gr...
Automated Aesthetic Quality Assessment (AQA) treats images primarily as static pixel vectors, aligning predictions with human-rating scores largely th...
Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks...
Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems...