2 papers
cs.CR2025
Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation
Yingjia Shang, Yi Liu, Huimin Wang +4
With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical…
cs.CL2025
Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
Shun Wang, Tyler Loakman, Youbo Lei +5
Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on do…