Artificial Intelligence Medical Compendium

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

Showing 19,331 to 19,340 of 214,800 articles

Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration

arXiv May 12, 2026
Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through empirical analys... read more 
Computer Vision and Pattern Recognition

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations

arXiv May 12, 2026
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from multi-view inc... read more 
Computer Vision and Pattern Recognition

Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances

arXiv May 12, 2026
Functional affordance grounding requires more than recognizing an object: an agent must localize the specific region that supports an interaction, such as the handle to pull or the button to press. This is difficult for training-free vision-language ... read more 
Computer Vision and Pattern Recognition

RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction

arXiv May 12, 2026
Histopathology whole-slide images (WSIs) are routinely acquired in clinical practice and contain rich tissue morphology but lack direct molecular architecture and functional programs defining pathological states, whereas RNA sequencing (RNA-seq) prov... read more 
Computer Vision and Pattern Recognition

Single-Shot HDR Recovery via a Video Diffusion Prior

arXiv May 12, 2026
Recent generative methods for single-shot high dynamic range (HDR) image reconstruction show promising results, but often struggle with preserving fidelity to the input image. They require separate models to handle highlights and shadows, or sacrific... read more 
Computer Vision and Pattern Recognition

Unlocking UML Class Diagram Understanding in Vision Language Models

arXiv May 12, 2026
Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard-ing diagrams compared to photos. Although progress has been made in the area of bar charts, line ... read more 
Computer Vision and Pattern Recognition cs.AI

ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes

arXiv May 12, 2026
We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executable drawing program that a deterministic evaluator re-renders and compares with the target. The v1... read more 
Computer Vision and Pattern Recognition

Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning

arXiv May 12, 2026
Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual representations. ... read more 
Computer Vision and Pattern Recognition cs.AI

WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting

arXiv May 12, 2026
Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely unverified. A... read more 
Computer Vision and Pattern Recognition cs.AI cs.GR

CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset Selection

arXiv May 12, 2026
The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a promising paradigm by identifying a highly informative coreset. However... read more 
Computer Vision and Pattern Recognition
Popular Topics
Recent Journals