Author

Xijia Tao

Observed name: Tao, Xijia

Institutions: City University of Hong Kong, Huazhong University of Science and Technology, University of Hong Kong

Observed institutions: City University of Hong Kong, Huazhong University of Science and Technology, University of Hong Kong

OpenAlex ID: A5101212446

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image

2025 · Xijia Tao, Shuai Zhong, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 61

PDF

Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability

2023 · Ye, Jiacheng, Tao, Xijia, et al. · arXiv (Cornell University) · 27

PDF

SoftSkill: Behavioral Compression for Contextual Adaptation

2026 · Tao, Xijia, Teng, Yihua, et al. · arXiv (Cornell University) · 6

PDF

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

2026 · Chen, Kecheng, Liu, Ziru, et al. · arXiv (Cornell University) · 2

PDF

Visual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom

2026 · Tao, Xijia, Teng, Yihua, et al. · arXiv (Cornell University)

PDF

How Should Diffusion Language Models Edit Code?

2026 · Tao, Xijia, Liu, Ziru, et al. · arXiv (Cornell University)

PDF

Works count: 9

Citation count: 139

H-index: 5

I10-index: 3