activity
20242026
collaborators

26 papers

cs.CL2026

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

Pengzhou Cheng, Haowen Hu, Zheng Wu +4

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cos…

cs.CL2026

MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft

Tianjie Ju, Yueqing Sun, Zheng Wu +7

Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic op…

cs.AI2026

HLL: Can Agents Cross Humanity's Last Line of Verification?

Xinhao Song, Su Su, Sirui Song +6

Multimodal agents are increasingly expected to operate interfaces on behalf of users, raising a central deployment question: can they truly substitute for humans in workflows that…

cs.CL2026

Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents

Zheng Wu, Pengzhou Cheng, Zongru Wu +5

Recent advancements in multimodal large language models (MLLMs) have shown exceptional potential in enabling mobile-using agents to autonomously execute human instructions. However…

cs.CR2026

GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning

Haodong Zhao, Tianyi Xu, Tianhang Zhao +2

Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely…

cs.AI2026

Faithful Mobile GUI Agents with Guided Advantage Estimator

Haowen Hu, Pengzhou Cheng, Zheng Wu +3

Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcut…