Haowen Hu — accepted AI-conference papers

2026

Faithful Mobile GUI Agents with Guided Advantage Estimator

Haowen Hu, Pengzhou Cheng, Zheng Wu, Lingzhong Dong, Gongshen Liu, Zhuosheng Zhang

ICML 2026poster

Vision-language model (VLM) based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displayed screen evidence or user instructions. To address this, we propose **F…

Cited by 0 Source ↗Scholar ↗

2025

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

Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Daizong Ding +2

EMNLP 2025

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 cost, users often rely on open-source GUI agents or APIs offered by AI providers, which introduces a critical but underexpl

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗