Jiaju Han

I am currently pursuing a second bachelor's degree in Data Science and Big Data Technology at China University of Petroleum (Beijing), after completing a B.A. in English at the same university. My current research interests focus on world models, robotics, and embodied AI.

I am currently looking for Fall 2027 PhD opportunities and research assistant positions.

Updates

  • Aug 2026 When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models has been accepted at ACM Multimedia 2026.
  • Aug 2026 Submitted 7 papers to AAAI 2027.
  • Jul 2026 Submitted 4 papers to ACCV.
  • Jun 2026 Submitted 2 papers to EMNLP 2026.
  • Jun 2026 Submitted 2 papers to the KDD Datasets and Benchmarks Track.
  • May 2026 Submitted 2 papers to NeurIPS.

Publications

XSPA teaser figure

AAAI 2027 Submission · arXiv Preprint

XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs

Chengyin Hu, Jiaju Han, Xuemeng Sun, Qike Zhang, Yiwei Wei, Ang Li, Chunlei Meng, Xiang Chen, Jiahuan Long

FusionRS dataset pipeline figure

KDD Datasets and Benchmarks Track Submission · arXiv Preprint

FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Cross-Modal Vision-Language Learning

Jiaju Han, Ben Zhang, Xuemeng Sun, Qike Zhang, Yuxian Dong, Chengyin Hu, Fengyu Zhang, Yiwei Wei, Jiujiang Guo

QR-STT figure 1

ACCV Submission · arXiv Preprint

QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models

Xiang Chen, Yingying Zhao, Chao Li, Jiaju Han, Ben Zhang, Ang Li, Jiahuan Long, Yiwei Wei, Jiujiang Guo, Chengyin Hu

InfraQR figure 1

ACCV Submission · arXiv Preprint

InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models

Xin Li, Jiaju Han, Ma Yaqi, Chengyin Hu, Yingying Zhao, Jiahuan Long, Fengyu Zhang, Yahui Chai

MonoIR-RS figure 1

ACCV Submission · arXiv Preprint

MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation

Jiaju Han, Ma Yaqi, Yahui Chai, Xuemeng Sun, Xin Li, Qike Zhang, Yingying Zhao, Xiang Chen, Luwei Yang, Chengyin Hu, Jiahuan Long

AirflowAttack figure 1

ACCV Submission · arXiv Preprint

AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models

Cong Su, Jiaju Han, Xuemeng Sun, Chengyin Hu, Qike Zhang, Jiujiang Guo, Yiwei Wei, Jiahuan Long

CFGPatch teaser figure

NeurIPS Submission · arXiv Preprint

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability

Xiang Chen, Yuxian Dong, Chao Li, Chengyin Hu, Jiaju Han, Fengyu Zhang, Yiwei Wei, Jiahuan Long, Jiujiang Guo

CloudWeb teaser figure

NeurIPS Submission · arXiv Preprint

From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG

Jiaju Han, Chao Li, Chengyin Hu, Qike Zhang, Xuemeng Sun, Xin Wang, Fengyu Zhang, Xiang Chen, Yiwei Wei, Jiahuan Long, Jiujiang Guo

When Surfaces Lie teaser figure

ACM MM Accepted · arXiv Preprint

When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models

Chengyin Hu, Xuemeng Sun, Jiaju Han, Qike Zhang, Xiang Chen, Xin Wang, Yiwei Wei, Jiahua Long

Research Experience

Shenzhen Research Institute of Big Data (SRIBD) and CUHK-Shenzhen

Jun 2026 - Present · Research Assistant

Working on world models, embodied intelligence, large language models, and power-system applications.

Investigating predictive modeling and decision-making for embodied and energy-system scenarios, including LLM- and GraphRAG-based power-system fault prediction with topology-aware evidence retrieval and interpretable risk diagnosis.

China University of Petroleum (Beijing)

Sep 2025 - Jun 2026 · Undergraduate Researcher · Advised by Chengyin Hu

Worked on multimodal learning and VLM robustness, focusing on visible, infrared, and remote-sensing vision-language models.

Led and co-led structured adversarial attack studies, built reproducible evaluation workflows across classification, captioning, and VQA, and contributed to problem formulation, experimental design, analysis, and writing for multiple conference papers.

Education

China University of Petroleum (Beijing) B.Eng. in Data Science and Big Data Technology, 2025 - 2027 · GPA: 3.77 · Rank: 2/71
China University of Petroleum (Beijing) B.A. in English, 2021 - 2025

Contact

I am currently looking for Fall 2027 PhD opportunities and research assistant positions.

Email: 1404293404 [at] qq [dot] com · hanjiaju05 [at] gmail [dot] com