5 papers
ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
Shijing Hu, Liang Liu, Zhu Meng +1
Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks…
Towards Efficient Multimodal Unified Reasoning Model via Model Merging
Qixiang Yin, Huanjin Yao, Jianghao Chen +3
Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large…
Post-TIPS Prediction via Multimodal Interaction: A Multi-Center Dataset and Framework for Survival, Complication, and Portal Pressure Assessment
Junhao Dong, Dejia Liu, Ruiqi Ding +6
Transjugular intrahepatic portosystemic shunt (TIPS) is an established procedure for portal hypertension, but provides variable survival outcomes and frequent overt hepatic encepha…
OLMA: One Loss for More Accurate Time Series Forecasting
Tianyi Shi, Zhu Meng, Yue Chen +5
Time series forecasting faces two important but often overlooked challenges. Firstly, the inherent random noise in the time series labels sets a theoretical lower bound for the for…
ICFNet: Integrated Cross-modal Fusion Network for Survival Prediction
Binyu Zhang, Zhu Meng, Junhao Dong +2
Survival prediction is a crucial task in the medical field and is essential for optimizing treatment options and resource allocation. However, current methods often rely on limited…