Multimodal Medical Applications
Integration of LLMs with medical imaging, structured data, and other modalities
Multimodal Medical Applications
Research on Large Language Models in Multimodal Medical Applications
Unlocking Time-Series Forecasting with LLMs
Transforming pre-trained language models into data-efficient forecasters
SAT: Revolutionizing Medical Image Segmentation
Universal segmentation of radiology scans using text prompts
Enhancing Gaze Estimation with AI
Using text-guided multimodal learning to improve accuracy and applications
Evaluating Truth in AI Summaries
Using LLMs to detect factual inconsistencies in generated content
Harnessing LLMs to Uncover Hidden Arguments in Social Media
A novel LLMs-in-the-loop approach for analyzing public discourse
Context-Aware Emotion Recognition
Leveraging Vision Language Models for Human-Level Emotional Understanding
AI-Powered Surgical Assistants
Enhancing Robotic Surgery with Advanced Vision-Language Models
EMERGE: Smarter Healthcare Predictions
Enhancing EHR analysis with retrieval-augmented generation
Advancing AI for Daily Living Activities
Specialized vision-language models for healthcare monitoring
Reducing Hallucinations in Medical AI
Chain-of-Medical-Thought Approach for Accurate Report Generation
Reimagining X-ray Reports
Advancing Radiology Report Generation with Robust Evaluation Methods
AI-Enhanced X-ray Analysis
Integrating Clinical Context with Radiology Images via LLMs
Enhancing Medical AI Diagnosis
Novel Prompting Strategies for Vision-Language Models in Healthcare
Evaluating Vision-Language Models in Medicine
A critical assessment of LVLMs for medical imaging
ECG-Chat: Transforming Cardiac Diagnosis
An AI model bridging ECG signals and natural language for enhanced medical insights
Advanced Few-Shot Medical Image Classification
A novel prompt-tuning approach for digital pathology with limited data
Enhancing Radiology Vision Models
Visual Prompt Engineering for Zero-Shot Medical Image Classification
NeuroLM: Bridging Brain & Language
First universal foundation model connecting EEG signals and natural language
Advancing CLIP Models for Mammography
Novel multi-view and multi-scale approaches for breast cancer screening
Advancing Surgical AI with Video-Language Models
Bridging knowledge gaps in surgical scene understanding through hierarchical augmentation
Advancing Eye Care with AI
New multimodal dataset empowers vision-language models in ophthalmology
Extending LLMs Beyond Text
Processing Continuous Vector Data with In-Context Learning
Reading Minds: From Brainwaves to Text
Leveraging LLMs to Decode Thoughts from EEG Signals
SlideChat: Revolutionizing Pathology Image Analysis
First AI assistant that can analyze gigapixel-scale whole-slide pathology images
VividMed: Revolutionizing Medical Visual AI
A versatile vision-language model designed specifically for healthcare applications
MMed-RAG: Enhancing Medical AI Accuracy
A versatile retrieval system for reducing hallucinations in medical image diagnosis
Synthetic Data Revolution in Medical AI
Building medical vision-language models without real patient data
Zero-Shot Video Action Detection
Leveraging Large Vision-Language Models without Training Data
AI Revolution in Colonoscopy
Advancing Medical Imaging Through Intelligent Systems
Region-Aware Medical Vision-Language Models
Enhancing interpretability through region-specific visual reasoning
Enhancing Medical AI with Bilinear Attention
A more efficient approach to medical visual question answering
3D Brain Mapping Innovation
AI-powered shape analysis of brain's white matter pathways
Unlocking 3D Medical Imaging with Self-Supervised Learning
Advancing MAE pre-training for more accurate medical image segmentation
Smart Federated Learning for Vision-Language Models
Optimizing Model Fine-tuning on Resource-constrained Devices
Medical Vision-Language Models: Beyond General AI
Specialized AI for Healthcare Precision
Advancing Medical AI with Vision-Language Models
A 5.5M-sample multimodal dataset revolutionizing medical AI capabilities
Smarter Cancer Diagnosis with Less Data
Knowledge-enhanced compression for few-shot learning in pathology
Automating Medical Image Analysis with AI
Teaching AI to adapt to biomedical imaging without extensive manual prompting
GEMeX: Advancing Medical Visual Question Answering
A groundbreaking benchmark for explainable chest X-ray diagnosis
Libra: Next-Gen Medical Image Analysis
Enhancing radiology reports through temporal image reasoning
Domain-Specific Multimodal LLMs
Enhancing Visual AI for Specialized Industries
Reducing AI Hallucinations in Medical Reporting
A novel uncertainty quantification approach for factual radiology reports
Reimagining EEG Decoding with Foundation Models
Criss-Cross Brain Modeling for Enhanced Brain Signal Interpretation
Predicting Infant Brain Development with AI
Novel transformer model predicts developmental outcomes from neonatal fMRI
Unlocking Biological Insights from AI Models
Using Dictionary Learning to Extract Concepts from Microscopy Foundation Models
MoColl: Smarter Medical Image Captioning
Combining Specialized and General Models for Better Results
Enhancing Medical AI Vision with Visual Prompts
Guiding AI's attention to specific regions in medical images
BIOMEDICA: Democratizing Biomedical AI
Creating Open Vision-Language Models from Scientific Literature
Face Understanding in AI Models
First comprehensive benchmark for evaluating facial analysis capabilities of multimodal LLMs
Advancing Fundus Image Analysis with AI
A novel approach to vision-language pretraining for ophthalmology
AI-Powered Tumor Detection
Foundation Models for Annotation-Free Brain Tumor Segmentation
Brain-Adapter: AI-Powered Neurological Analysis
Adapting Multimodal Large Language Models for 3D Brain Imaging
Solving the Rare Medical Event Challenge
Using LLMs to Generate Custom Prompts for Zero-Shot Medical Image Classification
AffectGPT: Advancing Emotion Intelligence
Multimodal Language Models for Enhanced Emotion Understanding
AIN: Advancing Arabic Multimodal AI
First comprehensive multimodal model designed specifically for Arabic language
DermaSynth: Advancing AI in Dermatology
Creating rich synthetic image-text pairs for vision LLMs in medicine
Optimizing Vision-Language Models
Automated selection of pretrained models for maximum performance
AI-Powered Visual Grounding in Medical Imaging
Automating the connection between radiological text and image locations
Personalizing Anomaly Detection
Improving few-shot anomaly detection through feature personalization
MedRAX: AI-Powered Chest X-ray Analysis
A versatile AI agent integrating multiple diagnostic tools for improved clinical decision-making
Language-Guided Image Registration
Using LLMs to Establish Spatial Correspondence Between Images
RadVLM: AI-Powered Radiology Assistant
A conversational AI model revolutionizing chest X-ray interpretation
MoFM: Revolutionizing Human Motion AI
A foundation model for complex human motion understanding
Emotion Intelligence in AI Vision-Language Models
Evaluating how well modern VLMs understand human emotions
AI-Powered Heart & Lung Sound Separation
Pioneering LLM Integration with NMF for Enhanced Medical Diagnostics
Bridging Vision and Text in Medical Imaging
Advanced AI framework enhances chest X-ray interpretation
ClinKD: Advancing Medical Visual AI
Distilling Clinical Knowledge for Better Medical Image Understanding
Boosting Vision-Language Models with Diffusion
How Lavender aligns attention mechanisms for 68% improvement in medical visual understanding
Revolutionizing Vision with Hyperspectral Imaging
How AI and Deep Learning Transform Multispectral Data Analysis
Universal Pathology Intelligence
Leveraging Multimodal LLMs to Revolutionize Digital Pathology
Multi-Granular Prompting for Medical Imaging
Advancing Few-Shot Pathology Classification with Vision-Language Models
Zero-Shot Anomaly Detection with MLLMs
Detecting anomalies without prior training data
Biologically-Inspired Digital Nose
Enhancing Odor Recognition with AI and Biological Principles
Bridging Vision & Language for Medical Image Analysis
A dual-scale approach to improve cancer classification from pathology images
BrainWavLM: Teaching AI to Think Like Humans
Fine-tuning speech models with actual brain response data
The Evolution of AI in Medicine
From text-only models to integrated multimodal systems
HealthGPT: Revolutionizing Medical AI
Unifying visual comprehension and generation in medicine through heterogeneous knowledge adaptation
Multi-Slide Pathology AI: PolyPath
Advancing AI to interpret multiple pathology slides simultaneously for comprehensive diagnosis
AI-Powered Medical Imaging Interpretation
Text-Guided Segmentation Across Medical Image Sequences
Advancing Medical Diagnostics with Multi-X-ray Analysis
A novel dataset for tracking disease progression through sequential X-rays
Mind Meets Machine: EEG-Powered Generative AI
Bridging brain signals with AI to revolutionize human-computer interaction
Zero-Shot Emotion Detection with LLMs
Using GPT-4o-mini to automatically annotate facial emotions in real-world scenarios
Synthetic Data for Cardiac Scar Detection
Leveraging natural language and domain knowledge to enhance medical imaging AI
Enhancing AI Medical Imaging with Knowledge Injection
Improving Chest X-ray classification through medical knowledge integration
Bridging the Gap: Multimodal Integration for Medical Data
How LLMs can fuse time series data with clinical notes in EHRs
Enhancing Visual Intelligence Through Self-Learning
Improving multimodal AI reasoning and explainability with synthetic data
FetalCLIP: Advancing Fetal Ultrasound Analysis
A novel vision-language foundation model for improved prenatal diagnostics
Fighting Medical AI Hallucinations
Visual Retrieval-Augmented Generation for More Accurate Medical AI
Attention-Enhanced Audio Processing
Teaching AI to Listen Like Humans
The Challenge of Small Visual Details
Understanding and enhancing MLLMs' perception capabilities
EEG Foundation Models
Leveraging Pretrained Models to Revolutionize Brain Activity Analysis
ECG-Expert-QA: Advancing Heart Disease Diagnosis with AI
A new benchmark for evaluating medical LLMs in electrocardiogram interpretation
Advancing ECG Analysis with AI
Knowledge-enhanced multimodal learning for flexible lead setups
Zero-Shot Fungal Classification
Enhancing Visual AI with Synthetic Data and Image Captioning
SuPreME: Revolutionizing ECG Analysis
Supervised pre-training for more accurate cardiac diagnoses
Automating Medical ML with Intelligent Agents
A multi-agent system that builds customized medical imaging models
Advancing Chest X-Ray Analysis with AI
Leveraging contrastive learning for temporal disease progression insights
Combating Medical Hallucinations in AI Vision Models
Introducing MedHallTune: A new benchmark for safer healthcare AI
Bridging the Gap in Pathology AI
A new visual grounding benchmark for precise pathology analysis
AI Revolution in Neuro-Trauma Triage
Foundation Model for Rapid, Accurate Head CT Analysis
Evaluating AI's Eye for Disease
First comprehensive benchmark for AI models in fundus image interpretation
Personalized Low-Dose CT Innovation
Combining LLMs with Federated Learning for Privacy-Preserving Medical Imaging
Overcoming Missing Data in Medical Predictions
A novel approach for survival prediction with incomplete multimodal data
Med-VLMs: The Future of Medical AI
Integrating Vision and Language for Enhanced Healthcare
Enhancing Medical AI Vision
Dual-level constraints for better biomedical visual question answering
RetinalGPT: AI-Powered Retinal Analysis
Advancing Eye Care with Specialized Multimodal AI
Enhancing Few-Shot Segmentation with LLMs
Bridging the gap between visual features and semantic understanding
Revolutionizing Medical Image Segmentation
Semi-supervised learning with SAM reduces reliance on expert annotations
Advanced Emotion Recognition with AI
Reinforcement Learning Enhances Multimodal Emotion Detection
Universal Text-Driven CT Segmentation
Bridging the gap between natural language and medical image analysis
GEM: Next-Generation ECG Interpretation
Advancing healthcare with multimodal AI that grounds diagnoses in ECG evidence
AI-Powered Early Detection of Cancer Cachexia
Multimodal approach integrates clinical data for improved patient outcomes
Fine-Grained Video Understanding for Security
New dataset enables precise video question answering for surveillance applications
AI-Human Partnership for Medical Imaging QC
A hybrid intelligence framework improving diagnostic accuracy
Eye on the Future: MLLMs in Ophthalmology
A specialized benchmark for evaluating AI models with ophthalmic imagery
LLMs Reimagine Text-to-Image Generation
Enabling Medical Imaging Without Architectural Redesign
Advancing Zero-Shot Radiology Recognition with AI
How LLaVA-RadZ improves medical image analysis without prior training
CLIMB: Unifying Multimodal Clinical Data
A comprehensive benchmark for next-generation clinical AI
AI-Powered Cancer Detection Through MRI
Advancing breast cancer diagnosis with generative AI and magnetic resonance imaging
Face-Focused AI: Next-Gen Video Understanding
Advancing security and medical applications through fine-grained facial analysis
Revolutionizing Brain-Image Alignment
Using Optimal Transport to Enhance Neural Information Processing
Zero-Shot Learning in Histopathology
Unlocking Medical Diagnosis Without Labeled Training Data
AI-Powered Surgical Workflow Analysis
Learning from Expert Knowledge through Video-Language Models
AI Transforms Brain MRI Analysis
Language Models Automating Radiology Report Classification
Benchmarking Histopathology Vision-Language Models
A comprehensive evaluation framework for medical AI
Revolutionizing Medical Imaging with Zero-Shot Learning
How CLIP Integration Improves Chest X-Ray Analysis Without Labeled Data
AI-Powered Medical Image Labeling
Automating Supervision for Abdominal CT Scans
Advancing Scientific AI with MicroVQA
A specialized benchmark for multimodal reasoning in microscopy research
Derm1M: Revolutionizing Dermatology AI
A million-scale dataset bridging visual diagnosis and clinical knowledge
Vision-Language Foundation Models for Retinal Screening
Context-aware AI enhancing ocular disease detection
CLIP Adaptation for Radiology Reports
Leveraging pre-trained vision-language models for medical imaging
CLIP for Medical Image Segmentation
Leveraging Vision-Language Models for Precise Lesion Identification
Personalizing Video AI for Identity Recognition
One-Shot Learning Enables Subject-Aware Video Understanding
Advancing Digital Pathology with AI
Multi-Modal Fine-Tuning for Enhanced Cancer Prediction
MEPNet: AI-Powered Brain CT Report Generation
Advancing accuracy through balanced medical entity representation
Expanding Vision AI with Retrieval-Augmented Generation
Enhancing AI vision capabilities through external knowledge integration
Advancing Medical Image Reporting with AI
Specialized architecture outperforms general models for medical report generation
Enhancing Vision with Context-Aware AI
Using Large Language Models to Transform Semantic Segmentation
Bridging Visual and Language Understanding
An efficient approach to aligning modalities in vision-language models
Unlocking Medical Imaging with AI
Using language to enhance MRI analysis without extensive annotations
Med3DVLM: Revolutionizing 3D Medical Imaging
Efficient vision-language modeling for volumetric medical data
Unsupervised Slide Representation Learning in Pathology
Advancing computational pathology through cross-modal learning
AXUNet: Advancing Brain Tumor Detection
Combining CNN and Self-Attention for Enhanced Medical Imaging
Cross-Language Emotion Recognition
Zero-Shot Detection Using LLMs & Contrastive Learning
Unlocking Eye Movement Data for AI
First-Ever Tokenization Strategy for Gaze Data in Large Language Models
Advancing Audio Intelligence
Enhanced auditory cognition in Audio Language Models
Combating Bias in AI Dermatology Diagnosis
Using Generative AI to Create Balanced Dermoscopic Images
Benchmarking Vision-Language Models for Surgery
First comprehensive evaluation of VLMs across surgical AI tasks
Enhancing Medical Report Generation with AI
Introducing perception and reflection-driven reasoning for radiology reports
Revolutionizing Medical Imaging with AI
Integrating Stable Diffusion into Electrical Impedance Tomography
Advancing Medical AI with Specialized Vision-Language Models
Purpose-built LVLMs for improved medical image analysis
Rethinking Vision-Language Models in Radiology
Evaluating the Reality of Text Integration in Medical Imaging
Lightweight AI for Medical Image Analysis
Advancing Medical VQA with Efficient Multimodal Architecture
Unlocking 3D Intelligence in LLMs
Expanding language models' capabilities into spatial reasoning
Bridging the Small Data Gap in Vision AI
Addressing the overlooked sweet spot of 100-1000 labeled samples
Advancing Multimodal Reasoning in Academia
New dataset challenges AI models with complex academic imagery
Face-LLaVA: Decoding Facial Communications
A multimodal AI that understands facial expressions and attributes
Zeus: AI-Powered Medical Image Analysis
Zero-shot multimodal segmentation using large language models
Smarter Radiology Reporting with LLMs
Cost-effective AI assistance for radiologists using retrieval-augmented generation
RadZero: Advancing Medical AI in Radiology
Zero-shot learning with explainable vision-language models
Enhancing Medical Image Translation
Preserving Anatomical Accuracy through Dynamic Frequency Balancing
Advancing Medical Image Captioning with AI
Dual-prompt enhancement for more accurate clinical descriptions
Reimagining Medical AI with Multi-annotation Data
Advancing multi-task capabilities in medical foundation models through data-centric innovation
Improving Medical AI Consistency
How LLMs Generate Better Medical Question-Answering Systems
