Jie Wang

I am a junior undergraduate student majoring in Computer Science and Technology at the College of Computer Science and Fan-Gongxiu Honors College, Beijing University of Technology.

I am currently a Research Assistant at the Beijing Institute of Artificial Intelligence, advised by Associate Researcher Jinduo Liu. My research focuses on multimodal learning, large language model security, and reinforcement learning.

In Summer 2025, I visited North Carolina State University as a Research Assistant under Dr. Muhammad Shahzad, where our work on WiFi-based gesture recognition won 1st Place in the Poster Symposium (1/50).

LLM security · multimodal learning · reinforcement learning · vision-tactile perception

I am interested in building AI systems that are safe, robust, and grounded across modalities, especially efficient safety evaluation for large language models and multimodal perception.

Research

My current research studies safe and robust AI systems across language, vision, and tactile modalities.

• LLM security and red-teaming: evaluating and improving model robustness against policy-violating or adversarial behavior.
• Multimodal learning: studying cross-modal safety alignment and perception with vision and tactile signals.
• Reinforcement learning: decision-making optimization and knowledge graph reasoning.

News

• [2026-07] Our paper EviGuard: Evidence-Guided Connector Intervention for Cross-Modal Safety Unlearning in Multimodal LLMs was accepted to ACM MM 2026.
• [2026-05] Paper BEACON: Budget-Efficient Discovery of Policy Violations in Large Language Models via Cognitive-Guided Monte Carlo Tree Search accepted to IJCAI 2026.
• [2026-03] Two papers on multimodal safety alignment and vision-tactile perception submitted to CCF-A conferences.
• [2026-01] Paper on efficient LLM safety evaluation is under review at a top-tier AI conference.
• [2025-11] Received Fan-Gongxiu Honors Scholarship and Xiaomi Entrepreneur Scholarship.
• [2025-08] Won 1st Place in Poster Symposium at U.S. GEARS Research Program @ NCSU for AttentiveCSI.
• [2025-08] Awarded National 2nd Prize in China Robot Competition and Artificial Intelligence Contest.
• [2025-02] Invention patent on intelligent vehicle decision-making passed preliminary examination.

Selected Publications

A more complete publication list is available on the publications page.

Education

• Beijing University of Technology, B.Eng. in Computer Science and Technology, Sept 2023 - June 2027 (expected). GPA: 4.00 / 4.00; Rank: 1st / 60.
• North Carolina State University, Visiting Research Assistant, June 2025 - August 2025. Supervised by Dr. Muhammad Shahzad.

Awards

• Best Poster Award (1st Place), U.S. GEARS Research Program @ NCSU, 2025.
• Fan-Gongxiu Honors Scholarship, 2025.
• Xiaomi Entrepreneur Scholarship, 2025.
• Study Excellence Scholarship, 2024 and 2025.
• National 2nd Prize, China Robot Competition and Artificial Intelligence Contest, 2025.
• Outstanding Student Honor, BJUT, 2024.

Skills

Python, C/C++, Java, MATLAB, Verilog HDL · PyTorch, TensorFlow, HuggingFace Transformers, Scikit-learn · Linux, Git/GitHub, Docker, LaTeX.

Languages: Chinese (native), English (IELTS 7.0; Reading & Writing 7.0).

Photos