4 papers
ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models
Yingxin Lai, Zitong Yu, Jun Wang +3
Multimodal Large Language Models (MLLMs) enable interpretable multimedia forensics by generating textual rationales for forgery detection. However, processing dense visual sequence…
Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection
Yingxin Lai, Zitong Yu, Jun Wang +3
Face forgery detection faces a critical challenge: a persistent gap between offline benchmarks and real-world efficacy,which we attribute to the ecological invalidity of training d…
Evaluating Recabilities of Foundation Models: A Multi-Domain, Multi-Dataset Benchmark
Qijiong Liu, Jieming Zhu, Yingxin Lai +5
Comprehensive evaluation of the recommendation capabilities of existing foundation models across diverse datasets and domains is essential for advancing the development of recommen…
SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models
Yichen Shi, Yuhao Gao, Yingxin Lai +7
Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks, capitalizing on their visual semantic comprehension and reasoning capabiliti…