Artificial Intelligence Medical Compendium

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

Showing 19,381 to 19,390 of 214,800 articles

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy

arXiv May 12, 2026
RLHF is widely used to align flow-matching text-to-image models with human preferences, but often leads to severe diversity collapse after fine-tuning. In RL, diversity is often assumed to correlate with policy entropy, motivating entropy regularizat... read more 
Computer Vision and Pattern Recognition

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning

arXiv May 12, 2026
Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to their abili... read more 
Machine Learning cs.AI cs.CV

MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation

arXiv May 12, 2026
Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There have been a number of recent works dealing with learning and composing multiple objects and patter... read more 
Computer Vision and Pattern Recognition cs.LG

STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts

arXiv May 12, 2026
We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone Hero / YARG charts for drums, guitar, bass, vocals, and keys without any oracle metadata. STRUM is a... read more 
Sound cs.LG eess.AS

Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models

arXiv May 12, 2026
Generating realistic and user-preferred advertisements is a key challenge in e-commerce. Existing approaches utilize multiple independent models driven by click-through-rate (CTR) to controllably create attractive image or text advertisements. Howeve... read more 
Computer Vision and Pattern Recognition cs.CL cs.IR

PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization

arXiv May 12, 2026
In visual localization, Absolute Pose Regression (APR) enables real-time 6-DoF camera pose inference from single images, yet critically depends on fine-tuning data quality and coverage. While recent methods leverage 3D Gaussian Splatting (3DGS) for n... read more 
Computer Vision and Pattern Recognition

PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior

arXiv May 12, 2026
Large language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate $individual$ privacy decisions is not well understood. In this paper, we address the problem of evaluating whether a core set of user persona... read more 
Cryptography and Security cs.LG

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model

arXiv May 12, 2026
In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive phenomenon: the pe... read more 
Computer Vision and Pattern Recognition

On What We Can Learn from Low-Resolution Data

arXiv May 12, 2026
Artificial intelligence systems typically rely on large, centrally collected datasets, a premise that does not hold in many real-world domains such as healthcare and public institutions. In these settings, data sharing is often constrained by storage... read more 
Machine Learning

Expected Batch Optimal Transport Plans and Consequences for Flow Matching

arXiv May 12, 2026
Solving optimal transport (OT) on random minibatches is a common surrogate for exact OT in large-scale learning. In flow matching (FM), this surrogate is used to obtain OT-like couplings that can straighten probability paths and reduce numerical inte... read more 
Machine Learning math.PR
Popular Topics
Recent Journals