7 papers
Assessing Privacy Preservation and Utility in Online Vision-Language Models
Karmesh Siddharam Chaudhari, Youxiang Zhu, Amy Feng +2
The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various util…
Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands
Kristin Qi, Youxiang Zhu, Caroline Summerour +2
Early detection of cognitive decline is crucial for enabling interventions that can slow neurodegenerative disease progression. Traditional diagnostic approaches rely on labor-inte…
Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning
Kristin Qi, Jiali Cheng, Youxiang Zhu +2
Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focuse…
Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts
Youxiang Zhu, Ruochen Li, Danqing Wang +2
Long-context large language models (LLMs) are prone to be distracted by irrelevant contexts. The reason for distraction remains poorly understood. In this paper, we first identify…
UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning
Kristin Qi, Youxiang Zhu, Xiaohui Liang
We present our approach to the PerAnsSumm Shared Task, which involves perspective span identification and perspective-aware summarization in community question-answering (CQA) thre…
Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection
Nana Lin, Youxiang Zhu, Xiaohui Liang +2
Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with sponta…