I am a PhD student in Computer Science at LMU Munich, supervised by Prof. Dr. Volker Tresp, where I study Language Models with a focus on their mechanistic interpretability, architectural designs, and post-training applications. My research interests lie in understanding the capabilities and limitations of language models, and from there developing new methods and solutions. Prior to this, I completed my M.Sc. in Data Engineering and Analytics at the Technical University of Munich, and my B.E. in Computer Science and Technology at Xi'an Jiaotong University.

• SIREN, a plug-and-play component that harnesses LLM internal representations for harmfulness detection
• Outperforming dedicated safety guardrails in performance, generalization, and efficiency

• A Routing-Free MoE architecture, eliminating routers, Softmax, TopK, and hard-coded load balancing
• A unified, adaptive load-balancing framework that jointly optimizes token- and expert-balancing
• Experiments and analyses demonstrating the improvements of Routing-Free MoE over baselines

• Dynamics between memory vectors in experts and expert vectors in routers when PEFTing to MoE LLMs
• A unified framework for integrating PEFT with MoE LLMs
• PERFT as a family of adaptation strategies, with extensive experiments validating effectiveness and scalability

• A lightweight plug-and-play text classification framework using LLM's internal representations
• Consistently outperforming conventional methods in performance, efficiency, and interpretability