About Me

Hi! I am Zhuoran Wang, a master student in Shool of Electrical Engineering, Mathematics and Computer Science at Delft University of Technology, majoring in Computer Engineering (now Computer and Embedded Systems Engineering).
Research Interests
My primary interest lies in AI and ML systems. Grounded in systems research, my work often extends to the algorithmic and application layers, aiming to
connect low-level optimization with higher-level design.
I am passionate about building, debugging, and improving complex systems, with a particular emphasis on enhancing the efficiency of large language model (LLM) inference and distributed training.
Central to my approach is a firm belief in the power of hardware-software-algorithm co-design. I am convinced that only by tightly integrating algorithm, software and hardware development can we achieve the level of efficiency and scalability necessary to democratize the use of LLMs, making them more accessible and effective for a wide range of applications.
I am actively seeking PhD/Mphil/RA position starting in 2025/2026 Fall.
Education
Experience
- [2025.02 - Present] Master Thesis Student, Delft University of Technology, The Netherlands
- Embedded Systems group, Department of Software Technology
- Working on the topic of Efficient Large Language Model Inference
- [2024.10 - 2025.03] Research Intern, Delft University of Technology, The Netherlands
- Distributed System group, Department of Software Technology
- Working on Decentralized Machine Learning Systems
- [2022.03 - 2022.06] Software Engineer Intern, Shandong University Tianyuan Digital Industry Research Institute, China
- Building website using SpringBoot, Vue and MySQL
- [2020.06 - 2020.09] Research Intern, Fuzhou University, China
- An introductory research on the topics of Computer Vision and Object Detection
Awards and Honors
- Kaggle Silver Medalist
- Kaggle Bronze Medalist
- Kaggle Expert
- Second Prize (Fujian Province), Undergraduate Mathematical Contest in Modeling
- Third Prize (National-level), Undergraduate Electrician Mathematical Contest in Modeling
- Third-class Scholarship, Fuzhou University
Publications
- Towards Dynamic KV-Cache Compression: Fine-Grained Evaluation of Key and Value Ranks in LLMs.
Jian Chen*, Zhuoran Wang*, Jiayu Qin, Ming Li, Meng Wang, Changyou Chen, Yin Chen, Qizhen Weng, Yirui Liu.
Conference on Neural Information Processing Systems (NeurIPS) workshop, 2025. (* equal contribution)
Academic Service
- Student Volunteer, ASPLOS / EuroSys 2025, Rotterdam, The Netherlands
Page design by Zhuoran Wang