Latest AI and machine learning research in covid-19 for healthcare professionals.
We present Moondream Segmentation, a referring image segmentation extension of Moondream 3, a vision-language model. Given an image and a referring expression, the model autoregressively decodes a vector path and iteratively refines the rasterized mask into a final detailed mask. We introduce a reinforcement learning stage that resolves ambiguity in the supervised signal by directly optimizing mas...
Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution shifts between generated and real images across scenarios, and such mismatches can markedly degrade downstream performance. To address this issue, we propose Al...
An assumption often made in supervised learning is that the training and testing sets have the same label distribution. However, in real-life scenario...
During the COVID-19 pandemic, reported incidence data played a central role in public health surveillance and in tracking epidemic dynamics, although ...
Background: Previous recommendations on screening for prostate cancer relied on ongoing trials of screening with prostate-specific antigen (PSA), whic...
Nuclei instance segmentation is critical in computational pathology for cancer diagnosis and prognosis. Recently, the Segment Anything Model has demon...
Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity...
Considering recent advances in remote sensing satellite systems and computer vision algorithms, many satellite sensing platforms and sensors have been...
The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authenticatio...
Few-shot medical image segmentation (FSMIS) has achieved notable progress, yet most existing methods mainly rely on semantic correspondences from scar...
Recently, crowd-sourced online criminal investigations have used generative-AI to enhance low-quality visual evidence. In one high-profile case, socia...
As multimodal misinformation becomes more sophisticated, its detection and grounding are crucial. However, current multimodal verification methods, re...
Longitudinal electronic health records (EHRs) form irregular event sequences that mix multiple clinical coding systems and care settings. Learning tra...
As computational tools and machine learning models for protein sciences continue to advance and proliferate, bench scientists face increasing technica...
Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mecha...
The genomic foundation model Evo 2 enables zero-shot variant effect prediction. Here, we evaluate its performance using Arabidopsis thaliana reproduct...
Out-of-distribution (OOD) detection aims to identify samples that deviate from in-distribution (ID). One popular pipeline addresses this by introducin...
Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-base...
Advanced driver assistance systems (ADAS) often rely on deep neural networks to interpret driving images and support vehicle control. Although reliabl...
The deep-learning based image matching networks can now handle significantly larger variations in viewpoints and illuminations while providing matched...