The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts

Authors: Yuchen Zhang, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Recommended citation: Yuchen Zhang, Yaxiong Wang, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng, "The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts." CVPR, 2026.

@inproceedings{wang2026UniAD,
author = "Zhang, Yuchen and Wang, Yaxiong and Wu, Yujiao and Wu, Lianwei and Zhu, Li and Zheng, Zhedong",
title = "The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts",
booktitle = "CVPR",
year = "2026" }