collaborators

7 papers

cs.CR2025

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs

Shuai Zhao, Xinyi Wu, Shiqian Zhao +4

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, ex…

cs.CR2025

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs

Man Hu, Xinyi Wu, Zuofeng Suo +5

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstr…

cs.AI2025

Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity

Shuai Zhao, Yulin Zhang, Luwei Xiao +7

Despite the remarkable progress of large language models (LLMs) across various domains, their capacity to predict retinopathy of prematurity (ROP) risk remains largely unexplored.…

cs.AI2025

From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEM

Xinyi Wu, Yanhao Jia, Luwei Xiao +3

In AI-facilitated teaching, leveraging various query styles to interpret abstract educational content is crucial for delivering effective and accessible learning experiences. Howev…

cs.CR2025

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models

Jinming Wen, Xinyi Wu, Shuai Zhao +2

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual ta…

cs.CL2025

Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning

Xinyi Wu, Yanhao Jia, Qinglin Zhang +3

Project-Based Learning (PBL) involves a variety of highly correlated multimodal data, making it a vital educational approach within STEM disciplines. With the rapid development of…