视觉大模型 / VLM

Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents

Xuan Wang, Siyuan Liang, Zhe Liu, Yi Yu, Aishan Liu, Yuliang Lu, Xitong Gao, Ee-Chien Chang

专题命中 GUI与屏幕智能体 ：VLM(title,abstract)；vision-language model(abstract)；分类 cs.AI

Comments 10 pages

Find Everything: A General Vision Language Model Approach to Multi-Object Search

Daniel Choi, Angus Fung, Haitong Wang, Aaron Hao Tan

专题命中 GUI与屏幕智能体 ：vision language model(title,abstract)

Comments 8 pages, 5 figures

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions

Xinbei Ma, Yiting Wang, Yao Yao, Tongxin Yuan, Aston Zhang, Zhuosheng Zhang, Hai Zhao

机构 * School of Computer Science（计算机学院） ； Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering（智能交互与认知工程重点实验室） ； Shanghai Jiao Tong University（上海交通大学） ； Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3（Web3可信数据流通与治理上海市重点实验室） ； GenAI, Meta（Meta GenAI） 纠错

专题命中 GUI与屏幕智能体 ：multimodal large language model(abstract)；MLLM(abstract)

Comments ACL 2025