Universal precautions

Refer to Anything with Vision-Language Prompts

Recent image segmentation models have advanced to segment images into high-quality masks for visual entities, and yet they cannot provide comprehensive semantic understanding for complex queries based on both language and vision. This limitation reduces their effectiveness in applications that require user-friendly interactions driven by vision-language prompts. To bridge this gap, we introduce ...

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multim...

The Latent Space Hypothesis: Toward Universal Medical Representation Learning

Medical data range from genomic sequences and retinal photographs to structured laboratory results and unstructured clinical narratives. Although th...

Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

3D reconstruction from in-the-wild images remains a challenging task due to inconsistent lighting conditions and transient distractors. Existing met...

Investigating Mask-aware Prototype Learning for Tabular Anomaly Detection

Tabular anomaly detection, which aims at identifying deviant samples, has been crucial in a variety of real-world applications, such as medical dise...

RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. ...

R2SM: Referring and Reasoning for Selective Masks

We introduce a new task, Referring and Reasoning for Selective Masks (R2SM), which extends text-guided segmentation by incorporating mask-type selec...

CLIP-driven rain perception: Adaptive deraining with pattern-aware network routing and mask-guided cross-attention

Existing deraining models process all rainy images within a single network. However, different rain patterns have significant variations, which make...

SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost

Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, exten...

Earley-Driven Dynamic Pruning for Efficient Structured Decoding

Large Language Models (LLMs) have shown remarkable capabilities, yet ensuring their outputs conform to strict structural or grammatical constraints ...

Peptides in plant-microbe interactions: Functional diversity and pharmacological applications.

As dynamic interfaces governing molecular recognition and signal transduction, interactions between plants and microbes fundamentally shape ecosystem ...

Coarse for Fine: Bounding Box Supervised Thyroid Ultrasound Image Segmentation Using Spatial Arrangement and Hierarchical Prediction Consistency.

Weakly-supervised learning methods have become increasingly attractive for medical image segmentation, but suffered from a high dependence on quantify...

An Intelligent Model of Segmentation and Classification Using Enhanced Optimization-Based Attentive Mask RCNN and Recurrent MobileNet With LSTM for Multiple Sclerosis Types With Clinical Brain MRI.

In healthcare sector, magnetic resonance imaging (MRI) images are taken for multiple sclerosis (MS) assessment, classification, and management. Howeve...

An Optimized Framework of QSM Mask Generation Using Deep Learning: QSMmask-Net.

Quantitative susceptibility mapping (QSM) provides the spatial distribution of magnetic susceptibility within tissues through sequential steps: phase ...

Development and Validation of an Explainable Machine Learning Model for Warning of Hepatitis E Virus-Related Acute Liver Failure.

BACKGROUND AND AIMS: Early identification of patients with acute hepatitis E (AHE) who are at high risk of progressing to hepatitis E virus-related ac...

Predicting host-pathogen interactions with machine learning algorithms: A scoping review.

BACKGROUND: Diseases caused by pathogenic microorganisms pose a persistent global health challenge. Pathogens exploit host mechanisms through intricat...

Spotlights on novel strategic innovations on the artificial intelligence and deep learning driven quality control focuses in transfusion medicine, to optimize blood component safety and efficacy and minimize the potential pitfalls.

Artificial intelligence (AI) combined with human intelligent, and machine learning (ML) are transforming quality control (QC) in transfusion medicine,...

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i.e. accu...

TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching

Tumor data synthesis offers a promising solution to the shortage of annotated medical datasets. However, current approaches either limit tumor diver...

Combining Deep Architectures for Information Gain estimation and Reinforcement Learning for multiagent field exploration

Precision agriculture requires efficient autonomous systems for crop monitoring, where agents must explore large-scale environments while minimizing...