5 papers
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
Fanxiao Li, Jiaying Wu, Tingchao Fu +3
Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts into subtasks, roles, dependenc…
What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews
Fanxiao Li, Jiaying Wu, Tingchao Fu +4
Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form j…
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
Tingchao Fu, Wenkai Wang, Fanxiao Li +6
Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from…
Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection
Fanxiao Li, Jiaying Wu, Tingchao Fu +3
The proliferation of multimodal misinformation poses growing threats to public discourse and societal trust. While Large Vision-Language Models (LVLMs) have enabled recent progress…
Proxy-Embedding as an Adversarial Teacher: An Embedding-Guided Bidirectional Attack for Referring Expression Segmentation Models
Xingbai Chen, Tingchao Fu, Renyang Liu +2
Referring Expression Segmentation (RES) enables precise object segmentation in images based on natural language descriptions, offering high flexibility and broad applicability in r…