Education01
Peking University · School of Computer Science
PhD student
Wuhan University · School of National Cyber Security
Undergraduate student
AI SECURITY · AI FOR SOFTWARE ENGINEERING · MULTI-AGENT SYSTEMS · AGENTIC REINFORCEMENT LEARNING
Secure, adaptive, and intelligent systems.
I am a PhD student in the School of Computer Science at Peking University. My research lies at the intersection of AI security, AI for software engineering, multi-agent systems, and agentic reinforcement learning, with a focus on building trustworthy, adaptive, and collaborative intelligent systems.
I am open to discussions and collaboration. If you are interested in working together, feel free to reach out.
Experience02
JD.com · TGT Talent Program
Intern
DiDi
Intern
Latest news
Paper acceptances
Two papers on federated graph learning and temporal point processes accepted by NeurIPS 2025.
Paper on VR security accepted by Ubicomp 2025.
Paper on LLM jailbreaks accepted by USENIX Security 2025.
Paper on temporal point processes accepted by AAAI 2025.
Honors & awards
Named one of Wuhan University’s Top Ten Outstanding Youth Students (10 selected university-wide).
Received Wuhan University’s Model Student Award (60 selected university-wide).
Awarded the “Role Model of Luojia” honor, received by only 10 students university-wide.
Awarded the Lei Jun Excellence Scholarship (¥100,000; 10 recipients university-wide, including 4 undergraduates).
Received the National Scholarship.
Selected publications
Coming soon
MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
Fengyuan Ran co-first author · NeurIPS 2025 · CCF-A
TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
Fengyuan Ran co-first author · NeurIPS 2025 · CCF-A
HT-Auth: Unobtrusive VR Headset Authentication via Subtle Head Tremors
Fengyuan Ran 2nd author · Ubicomp / IMWUT 2025 · CCF-A
PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
Fengyuan Ran 4th author · USENIX Security Symposium 2025 · CCF-A
A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes
Fengyuan Ran 5th author · AAAI 2025 · CCF-A
The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
Fengyuan Ran 2nd author · under review
Research interests
AI for Software
Engineering
Building intelligent tools and agents that make software development more reliable and efficient.
Multi-Agent
Systems
Designing collaborative, adaptive agents that reason and act in changing environments.
Agentic Reinforcement
Learning
Learning robust policies for agents that plan, interact, and improve through experience.
AI Security
Understanding vulnerabilities in intelligent systems and designing more trustworthy defenses.
Personal archiveA visual note
A little more
Research should be rigorous, useful, and open to conversation.
My work sits between machine learning, security, and intelligent systems. I enjoy turning hard technical questions into methods that are both principled and practical.
Start a conversation