Scholar
Taiyi Wang
Google Scholar ID: lkVmQH8AAAAJ
Computer Lab, University of Cambridge
Citations & Impact
Citations
133
H-index
6
i10-index
5
Publications
16
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 1. OCMDP: Observation-Constrained Markov Decision Process, IJCNN 2025; 2. ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments, MLSys 2025; 3. A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning-Enhanced Approach, SIGMOD 2025, Awarded by SIGMOD 2025 Student Grant; 4. DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents, ICLR 2025.
Research Experience
- Currently a Research Scientist Intern at the Autonomous Agents Team, Google DeepMind, London, UK.
Education
- PhD: Computer Science and Technology, University of Cambridge, Advisor: Dr. Eiko Yoneki; Master's: Engineering, Johns Hopkins University, Graduated as the top 1 student in the class; Bachelor's: Physics, Peking University, Minor in Math, Honored with the Excellent Graduate Student Award and Excellent Graduation Thesis Award.
Background
- Research Interests: Reinforcement Learning, Machine Learning, Machine Learning Systems, and the enhancement of real systems (e.g., Database, LLM fine-tuning, LLM serving) through machine learning techniques, especially ML4Sys (especially RL4Sys). Brief Introduction: PhD Student at the Department of Computer Science and Technology, University of Cambridge, Co-Founder of Powersense.Ltd.
Miscellany
- Interests and Activities: Passionate about sports, Captain of the Girton College Men 1st Tennis Team.
