Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 17,031 to 17,040 of 213,633 articles

Generation Navigator: A State-Aware Agentic Framework for Image Generation

arXiv
Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting or closed-l... read more 

A More Word-like Image Tokenization for MLLMs

arXiv
Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form a... read more 

Counting Machine Parts

arXiv
Counting objects in an image is a task applicable across many domains. For instance, crowd counting, inventory counting, and cell counting have been the focus of recent research. The major challenges in estimating the count of objects include overlap... read more 

SkyNative: A Native Multimodal Framework for Remote Sensing Visual Evidence Reasoning

arXiv
Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoning. While effective for scene-level understanding, this pipeline may prematurely compress local vi... read more 

SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain

arXiv
Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external tools, and reason over retrieved information. Yet existing benchmarks rarely evaluate this ability in... read more 

UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction

arXiv
Feed-forward 3D reconstruction has recently demonstrated strong generalization across diverse scenes, yet its performance in UAV imagery remains underexplored due to distinctive acquisition geometries, large viewpoint variations, and ambiguity betwee... read more 

Domain Transfer Becomes Identifiable via a Single Alignment

arXiv
Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and cross-platform medical imaging. However, DT is fundamentally ill-posed: push-forward mappings are g... read more 

SurgLQA: Scalable Long-Horizon Surgical Video Question Answering

arXiv
Surgical Video Question Answering (VideoQA) provides a promising paradigm for dynamic intraoperative interpretation, enabling real-time decision support and context-aware retrieval in clinical environments. Nevertheless, existing approaches are predo... read more 

Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation

arXiv
Few-Shot Medical Image Segmentation (FSMIS) aims to delineate novel anatomical targets from one or a few annotated support images, addressing the annotation scarcity in medical imaging. Notwithstanding recent advancements, current prototype-based met... read more 

DCFold: Efficient Protein Structure Generation with Single Forward Pass

arXiv
AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has established AlphaFold3 as a foundation model for diverse generation a... read more