Image forensics has become increasingly challenging in the era of heterogeneous manipulations, where editing, AI-generated content, and deepfake synthesis expose highly diverse forensic cues across tracks and samples. Existing methods predominantly follow a static one-shot paradigm, in which all inputs are processed wi...
Jia-Feng Li, Kai Li, Ying Wen· Proceedings of the 34th ACM...· 0 citations
This work proposes SAFER (Sequential Adaptive Forensic Evidence Reasoner), a prior-guided forensic agent that reformulates forgery analysis as a budget-aware sequential evidence reasoning problem that achieves robust performance across diverse scenarios, while providing a more favorable accuracy--efficiency trade-off t...
Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images. While token pruning has emerged as a promising approach to reduce the inference cost of MLLMs, existing methods typically reassign position embeddings to the retained t...
Ya-Hong Wang, Zhang-Kai Ni, Jun-Cheng Wu et al.· 0 citations
LoMeVQA, a comprehensive benchmark consisting of 206K longitudinal visual question answering (VQA) pairs for temporal medical image analysis, is proposed and MedLong-8B, which achieves state-of-the-art performance across all tasks is introduced.
Zhilin Wu, Zhangkai Ni, Cheng Yang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.