7 papers
GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?
Yueying Zou, Pei Pei Li, Zekun Li +4
In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting…
AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents
Xuannan Liu, Xiao Yang, Zekun Li +2
As LLM-based agents operate over sequential multi-step reasoning, hallucinations arising at intermediate steps risk propagating along the trajectory, thus degrading overall reliabi…
T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search
Xing Cui, Yueying Zou, Zekun Li +4
Real-world multimodal misinformation often arises from mixed forgery sources, requiring dynamic reasoning and adaptive verification. However, existing methods mainly rely on static…
Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
Xuannan Liu, Zekun Li, Zheqi He +6
The increasing deployment of Large Vision-Language Models (LVLMs) raises safety concerns under potential malicious inputs. However, existing multimodal safety evaluations primarily…
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
Qianrui Teng, Xing Cui, Xuannan Liu +4
Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy. Althou…
Survey on AI-Generated Media Detection: From Non-MLLM to MLLM
Yueying Zou, Peipei Li, Zekun Li +5
The proliferation of AI-generated media poses significant challenges to information authenticity and social trust, making reliable detection methods highly demanded. Methods for de…