I am a Postdoctoral Researcher at King’s College London, working under the supervision of Dr. Yali Du. My research focuses on Multi-Agent Systems and Large Language Model (LLM) Security, with particular interests in multi-agent collaboration, agent coordination, and the security and trustworthiness of LLM-based systems.
I received my Ph.D. from the University of Chinese Academy of Sciences (UCAS), where my research focused on network traffic identification and tracking. I subsequently worked on information retrieval at Huawei, which led to my broader research interests in natural language processing and large language models.
I have published over ten research papers in deep learning and large language models. I actively contribute to the research community as a Senior Program Committee (SPC) member of AAMAS and a reviewer for leading conferences, including ICLR and ACL.
Recent activities
-
8 Dec 2026
1. Programme Chair of Workshop "Multi-Agent AI for Scientific Discovery", ELLIS Unconference 2026 · Paris, France
-
24–25 Nov 2026
1. Attended UKAIRS 26, organized by the University of Edinburgh
2. A paper was submitted and accepted -
19 Oct 2026
1. Attended Olympia AI Live
-
5–9 Oct 2026
1. Attended Oxford University BOLD Collaboration Week
2. Organized the Multi-agent Distributed Security Workshop -
10 Sep 2026
1. Attended UCL SOFAIR Launch Event
-
3 Aug 2026
1. Attended Oxford University BOLD
Recently published papers
- 2026 MIND: An Evidence-State Decision Interface for Criteria-Grounded Psychiatric Inquiry and Diagnosis
- 2026 The Local–Global Alignment Paradox: Evaluating Distributed Safety Reconstruction in Multi-Agent Systems
- 2026 Knowledge-Enhanced Image Captioning with Adaptive Graph-based Multimodal Alignment and LLM
- 2026 FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs
- 2026 PrivacyShadow: Revealing Fine-Tuning Leakage in Vision-Language Models Via Dual-Level Black-Box Attacks
- 2026 When Do PEFT Adaptations Leak Structure? Measuring Black-Box Structural Bounds in Public-Base Model Services
- 2026 MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation