Zeyu Pan

2 accepted papers

2026

MVP: Multiple View Prediction Improves GUI Grounding

Yunzhu Zhang, Zeyu Pan, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Linchao Zhu

CVPR 2026

GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction instability--minor visual perturbations (e.g., cropping a few p

Cited by 0 Source ↗code ↗Scholar ↗

2024

Detecting Machine-Generated Long-Form Content with Latent-Space Variables

Yufei Tian, Zeyu Pan, Nanyun Peng

EMNLP 2024finding

The increasing capability of large language models (LLMs) to generate fluent long-form texts is presenting new challenges in distinguishing these outputs from those of humans. Existing zero-shot detectors that primarily focus on token-level distributions are vulnerable to real-world domain shift inc…

Cited by 1 Source ↗PDF ↗Scholar ↗