352 citations · 1k across the 42 of their papers we have counts for
3 papers · 1 filter
AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech
Praphul Singh, Akshat Agarwal, Ratul Ghosh +5
Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical evidence. Protecting that spe…
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
Ashwin Kumar, Robbie Holland, Corey Barrett +8
Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-style finetuning. This two-sta…
From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarization
Qianqi Yan, Huy Nguyen, Sumana Srivatsa +3
Deploying multimodal large language models (MLLMs) for clinical summarization demands not only fluent generation but also transparency about where each statement originates-and a m…