Latest AI and machine learning research in medical education for healthcare professionals.
Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders struggle with fixed resolution pretraining, visual shortcut learning, weak visual grounding, and multilingual visual text understanding. In this work, we investigate the fundamental design principles required for robust visual text representation learning....
Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the c...
Histopathological whole slide images (WSIs) are central to cancer diagnosis, but their gigapixel scale, tissue heterogeneity, weak slide-level supervi...
Background. Cardiovascular-outcomes trials are lengthy, costly, and associated with substantial uncertainty prior to readout. In-silico trial simulati...
Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to repro...
The advancement of Embodied AI necessitates high-quality simulation assets that faithfully mirror the real world. However, transforming raw visual obs...
Imputing physiological time series (arterial blood pressure, blood glucose, etc.) is essential for addressing the missingness that pervades clinical d...
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore ho...
Self-supervised pretraining on remote sensing imagery typically treats all samples as equally informative, despite large variability in geographic and...
Myocardial scar segmentation from single-stack late gadolinium-enhanced cardiac magnetic resonance (LGE-CMR) imaging has been a longstanding and clini...
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore ho...
Educational visual question answering, or VQA, requires models to solve curriculum-oriented multiple-choice questions using both language and visual e...
Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically o...
Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with ...
While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent ...
While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates signif...
Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring the...
IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in ...
Robust navigation policies for autonomous agents must generalize across continuously varying environmental conditions such as turn rates, obstacles, f...
The generation of mathematically precise diagrams from tex- tual prompts has emerged as a critical yet underexplored capability of Large Language Mode...