Artificial Intelligence Medical Compendium

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

Showing 50,251 to 50,260 of 224,814 articles

Elastic Diffusion Transformer

arXiv
Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and distillation, typically rely on a fixed computational capacity, leading ... read more 

Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization

arXiv
Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to contaminate non-facial region... read more 

Named Entity Recognition for Payment Data Using NLP

arXiv
Named Entity Recognition (NER) has emerged as a critical component in automating financial transaction processing, particularly in extracting structured information from unstructured payment data. This paper presents a comprehensive analysis of state... read more 

A Deployment-Friendly Foundational Framework for Efficient Computational Pathology

arXiv
Pathology foundation models (PFMs) have enabled robust generalization in computational pathology through large-scale datasets and expansive architectures, but their substantial computational cost, particularly for gigapixel whole slide images, limits... read more 

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

arXiv
We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets each token represent up to $2^{256}$ states, yielding a compact yet hi... read more 

Restoration Adaptation for Semantic Segmentation on Low Quality Images

arXiv
In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic structures and high-frequency details. Although image restoration techniques offer a promising... read more 

CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learning

arXiv
Image editing has achieved impressive results with the development of large-scale generative models. However, existing models mainly focus on the editing effects of intended objects and regions, often leading to unwanted changes in unintended regions... read more 

ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization

arXiv
Existing Multimodal Large Language Models (MLLMs) for image forgery detection and localization predominantly operate under a text-centric Chain-of-Thought (CoT) paradigm. However, forcing these models to textually characterize imperceptible low-level... read more 

GeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction

arXiv
Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware self-corr... read more 

EgoSound: Benchmarking Sound Understanding in Egocentric Videos

arXiv
Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in vision-language understanding. Yet, human perception is inherently multisensory, integrating sight, sound, and motion to reason about the world. Among these modali... read more