Publications

Taiyi Wang, Liang Liang, Guang Yang, Thomas Heinis, Eiko Yoneki. “A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning-Enhanced Approach”. SIGMOD 2025.
Taiyi Wang, Zhihao Wu, Jianheng Liu, et al. “DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents”. ICLR 2025.
Youhe Jiang, Fangcheng Fu, Xiaozhe Yao, Taiyi Wang, Bin Cui, Ana Klimovic, Eiko Yoneki. “ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments”. MLSys 2025.
Taiyi Wang, Jianheng Liu, Bryan Lee, Zhihao Wu, Yu Wu. “OCMDP: Observation-Constrained Markov Decision Process”. IJCNN 2025.

Taiyi Wang, Eiko Yoneki. “IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse Workloads”. EuroMLSys 2024.
Taiyi Wang, Eiko Yoneki. “Enhancing Generalization through Task Vector Fusion in Deep Reinforcement Learning for Database Optimization”. EuroSys 2024 (Poster).

Ali Hadian, Behzad Ghaffari, Taiyi Wang, Thomas Heinis. “COAX: Correlation-Aware Indexing on Multidimensional Data with Soft Functional Dependencies”. DBML@ICDE 2023.
Hao Sun, Taiyi Wang. “Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference”. NeurIPS 2022 Workshop DeepRL.
Hao Sun, Ziping Xu, Meng Fang, Zhenghao Peng, Taiyi Wang, Bolei Zhou. “Constrained MDPs can be Solved by Early-Termination with Recurrent Models”. NeurIPS 2022 Workshop FMDM.
Hao Sun, Ziping Xu, Taiyi Wang, Meng Fang, Bolei Zhou. “Supervised Q-Learning can be a Strong Baseline for Continuous Control”. NeurIPS 2022 Workshop FMDM.
Taiyi Wang, Jiahao Shi. “Solving Maximal Stable Set Problem via Deep Reinforcement Learning”. ICAART 2020.
Taiyi Wang, Yajun Fang, Berthold KP Horn. “Why do we need bilateral control? In view of energy consumption”. IEEE UV 2018.