-
When AI Radiologists Get Confused: The Critical Challenge of VLM Robustness in Medical Diagnostics
-
Multimodal Large Language Models in Healthcare: Current Applications and Validation Approaches
A comprehensive review of multimodal LLMs in healthcare, covering vision-language models for medical imaging, EHR analysis tools, and clinical validation datasets for safe deployment.
-
The Evolution of Adversarial Robustness: From Neural Networks to Vision-Language Models
Tracing the evolution of adversarial robustness research from early neural networks to modern vision-language models, with key insights for building safe AI in healthcare applications.
-
Large Language Models: From Architecture to Evaluation
A complete guide to building and evaluating large language models, from pretraining and instruction finetuning to multimodal capabilities using LLaMA as a case study.
-
MLLMGuard: A Comprehensive Safety Framework for Multimodal Large Language Models