Artificial Intelligence Medical Compendium

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

Showing 18,431 to 18,440 of 214,278 articles

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

arXiv May 14, 2026
Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers ... read more 
Machine Learning cs.CV

Computational Imaging Priors for Wireless Capsule Endoscopy: Monte Carlo-Guided Hemoglobin Mapping for Rare-Anomaly Detection

arXiv May 14, 2026
Background. RGB-trained capsule-endoscopy classifiers underperform on small-vessel vascular findings by conflating hemoglobin contrast with bile and illumination falloff. Thus, here we test whether a Monte Carlo-inspired analytic model can comput... read more 
Computer Vision and Pattern Recognition

Does Synthetic Layered Design Data Benefit Layered Design Decomposition?

arXiv May 14, 2026
Recent advances in image generation have made it easy to produce high-quality images. However, these outputs are inherently flattened, entangling foreground elements, background, and text within a fixed canvas. As a result, flexible post-generation e... read more 
Computer Vision and Pattern Recognition

Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment

arXiv May 14, 2026
Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions like sepsis. While unstructured clinical narratives offer semantically rich and contextually complete d... read more 
Computation and Language cs.AI cs.LG stat.ML

Evidential Reasoning Advances Interpretable Real-World Disease Screening

arXiv May 14, 2026
Disease screening is critical for early detection and timely intervention in clinical practice. However, most current screening models for medical images suffer from limited interpretability and suboptimal performance. They often lack effective mecha... read more 
Computer Vision and Pattern Recognition cs.AI cs.LG

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

arXiv May 14, 2026
Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines o... read more 
Computer Vision and Pattern Recognition

Aligning Latent Geometry for Spherical Flow Matching in Image Generation

arXiv May 14, 2026
Latent flow matching for image generation usually transports Gaussian noise to variational autoencoder latents along linear paths. Both endpoints, however, concentrate in thin spherical shells, and a Euclidean chord leaves those shells even when prep... read more 
Computer Vision and Pattern Recognition

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding

arXiv May 14, 2026
Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain unconditional. We observe that ... read more 
Computer Vision and Pattern Recognition cs.LG

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

arXiv May 14, 2026
Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is computationally expensi... read more 
Computer Vision and Pattern Recognition cs.AI cs.CL

Towards Fine-Grained and Verifiable Concept Bottleneck Models

arXiv May 14, 2026
Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to the correct ... read more 
Machine Learning cs.AI
Popular Topics
Recent Journals