8 citations · 11 across the 5 of their papers we have counts for
5 papers
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Hao Li, Jingkun An, Zijun Song +8
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual object…
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
Xijie Huang, Xinyuan Wang, Hantao Zhang +6
Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in…
AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation
Jingkun An, Yinghao Zhu, Zongjian Li +6
Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality…
Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data
Yinghao Zhu, Zixiang Wang, Junyi Gao +6
The inherent complexity of structured longitudinal Electronic Health Records (EHR) data poses a significant challenge when integrated with Large Language Models (LLMs), which are t…
MFair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive-Attribute Reweighting Method
Yinghao Zhu, Jingkun An, Enshen Zhou +8
In the data-driven artificial intelligence paradigm, models heavily rely on large amounts of training data. However, factors like sampling distribution imbalance can lead to issues…