Artificial Intelligence Medical Compendium

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

Showing 10,691 to 10,700 of 209,601 articles

DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction

arXiv May 26, 2026
Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We propose DelowlightS... read more 
Computer Vision and Pattern Recognition

RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models

arXiv May 26, 2026
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve FLOPs, remai... read more 
Machine Learning

JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search

arXiv May 26, 2026
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while achieving substantially higher inference efficiency on high-resolutio... read more 
Computer Vision and Pattern Recognition cs.AI

DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding

arXiv May 26, 2026
Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only implicitly a... read more 
Computer Vision and Pattern Recognition

Memory-Distilled Selection for Noise-Robust Anomaly Detection

arXiv May 26, 2026
Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfectly clean training sets is impractical. However, existing methods are sensitive to contamination,... read more 
Computer Vision and Pattern Recognition

PinPoint: Prompting with Informative Interior Points

arXiv May 26, 2026
Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask generation. Prior training-free instances of this recipe consistently trail... read more 
Computer Vision and Pattern Recognition cs.CL

Model Merging on Loss Landscape: A Geometry Perspective

arXiv May 26, 2026
Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscape or rely on intractable full-space Hessian approximations. We propose... read more 
Machine Learning cs.AI stat.ML

Image Feature Fusion-based Federated Client Unlearning (FCU)

arXiv May 26, 2026
Major data protection regulations all mention the "right to be forgotten," and that's what pushed federated unlearning (FU) techniques forward. But one stubborn issue remains: catastrophic forgetting--you erase the target knowledge, yet somehow you a... read more 
Machine Learning

Joint 2D-3D Segmentation and Association in Street-level Imaging

arXiv May 26, 2026
Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that integrate... read more 
Computer Vision and Pattern Recognition

Measuring Prediction Uncertainty in Neural Cellular Automata

arXiv May 26, 2026
Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when a prediction should be trusted. Here, we study uncertainty estimation for NCA-based medical image s... read more 
Image and Video Processing cs.AI cs.CV
Popular Topics
Recent Journals