Hey, I’m a second year Ph.D. student at Trustworthy Autonomous Systems Laboratory, University of California, Riverside. It is my honor to be advised by Prof. Jiachen Li.

My research interest lies in the confluence of autonomous agents and multiagent systems, focusing on leveraging efficient multi-agent communication to develop robust algorithms for collaboratively solving perception, prediction, and decision-making challenges in real-world scenarios.

Previously, I earned my Master of Science degree in Computer Science from the New York University in 2023, where I was also interested on assessing the robustness of LLMs, with a particular interest in identifying and generating adversarial prompts that could mislead the models and even generate harmful content.

🔥 Research Interests

BEV Perception, Cooperative Perception, Occupancy Prediction
Trajectory Prediction and Planning
Multi-Agent Social Navigation
Trustworthy LLM/VLM (misinformation, hallucination, out of domain)

📝 Recent Projects

CMP: Cooperative Motion Prediction with Multi-Agent Communication
- A practical, latency-robust framework for cooperative motion prediction, which leverages the information shared by multiple CAVs to enhance perception and motion prediction performance.
- Address the unified problem where CAVs share information in both perception and prediction modules.
- Extensive experiments and ablation studies on the OPV2V and V2V4Real to demonstrate the effectiveness.
Auto-generation of jailbreaking prompts by combining token-based learning and sampling strategy.
- Despite advancements in safety alignment, Large Language Models (LLMs) are vulnerable to jailbreak attacks using specifically designed prompts. Current state-of-the-art prompt optimization techniques, focusing on token-wise loss, often result in easily detectable prompts by perplexity-based defenses. This study investigates generating effective and semantically meaningful adversarial prompts by sampling from successful hand-crafted examples while remaining different levels of similarity, aiming to preserve their efficacy while enhancing meaningfulness.

📝 Service

RA-L reviewer
ICLR 2025 reviewer

💻 Past Experiences

2023.01 - 2023.06, Research Assistant, NYU Multimedia and Visual Computing Lab at NYU, Advisor: Prof. Yi Fang.
2022.06 - 2022.08, Machine Learning Engineer Intern at Chatkick, Inc. New York, NY
2022.01 - 2022.05, Teaching Assistant for CS-GY 6573 at NYU
2020.12 - 2021.05, Machine Learning Engineer at Pingan Technology Co., Ltd. Beijing, China
2020.06 - 2020.10, Golang R&D engineer at ByteDance Co., Ltd. Beijing, China

🎖 Selected Awards

Dean’s Distinguished Fellowship (2023)
Merit Scholarship (2021)
Outstanding Graduates (2020)
National Scholarship (2019)

📖 Educations