Latest AI and machine learning research in ophthalmology for healthcare professionals.
Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial attacks, particularly those exploiting both modalities, remains underexplored, posing risks to critical applications like autonomous driving and content moderat...
Mean Deviation (MD) is a critical metric for assessing visual field loss in ophthalmology. While previous work has focused solely on predicting MD from Optical Coherence Tomography (OCT), it is intuitive to assume that combining OCT with another imaging of fundus photography (FP) could improve performance, as two ophthalmic medical imaging provide complementary information. This is particularly ex...
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention ...
Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to ...
Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry n...
Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularl...
Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in real...
Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing...
Small aerial robots are particularly well-suited for search and rescue in confined and hazardous environments due to their agility, low cost, and abil...
Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural per...
Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-...
Adapting large vision-language models (VLMs) such as CLIP to downstream tasks remains challenging, as full fine-tuning is computationally prohibitive ...
Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tas...
Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperf...
3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language des...
Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual revi...
While multimodal data integrating diverse imaging and clinical tabular records is crucial for accurate medical diagnosis, the arbitrary absence of spe...
Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process t...
Purpose: Psychological distress is highly prevalent in glaucoma and is associated with worse adherence, reduced quality of life, and faster disease pr...
Background. This study examines a competition based model (Cmodel) designed to capture the temporal dynamics of successive brain microstates derived f...