6 papers
UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models
Lei Tan, Shuwei Li, Mohan Kankanhalli +1
Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most e…
RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
Danni Xu, Shaojing Fan, Harry Cheng +1
Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce \textbf{RW-Post}, a post-aligned…
RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
Danni Xu, Shaojing Fan, Harry Cheng +1
Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--im…
Aggregating Diverse Cue Experts for AI-Generated Image Detection
Lei Tan, Shuwei Li, Mohan Kankanhalli +1
The rapid emergence of image synthesis models poses challenges to the generalization of AI-generated image detectors. However, existing methods often rely on model-specific feature…
A New Dataset and Benchmark for Grounding Multimodal Misinformation
Bingjian Yang, Danni Xu, Kaipeng Niu +3
The proliferation of online misinformation videos poses serious societal risks. Current datasets and detection methods primarily target binary classification or single-modality loc…
Modeling Human Responses to Multimodal AI Content
Zhiqi Shen, Shaojing Fan, Danni Xu +2
As AI-generated content becomes widespread, so does the risk of misinformation. While prior research has primarily focused on identifying whether content is authentic, much less is…