Zilong Wang
PhD Student in Computer Science
Shanghai Jiao Tong University
I work on sequential decision-making under uncertainty, with a focus on multi-armed bandits, matching markets, reinforcement learning, and efficient LLM reasoning.
John Hopcroft Center · advised by Prof. Shuai Li
Research: Multi-Armed Bandits · Matching Markets · Reinforcement Learning · LLM Reasoning
About
I am a PhD student in Computer Science at the John Hopcroft Center , Shanghai Jiao Tong University , advised by Prof. Shuai Li since September 2023.
Broadly, I am interested in how learning agents can make reliable and efficient decisions with uncertainty, limited feedback, and limited resources. My current research spans bandit learning in matching markets, reinforcement learning, and efficient reasoning for large language models.
News
BORA-BUDGET: Learning When to Think Under a Token Budget accepted to EMNLP 2026 Main Conference.
Anytime-Valid Multi-Objective Online Experimentation with Contrast Certificates accepted to CIKM 2026.
Bandit Learning for Online Scheduling with Immediate Decision accepted to UAI 2026.
Optimal Algorithm for Max-Min Fair Bandit accepted to ICML 2025.
Publications
Google Scholar ↗2026
Anytime-Valid Multi-Objective Online Experimentation with Contrast Certificates
Bandit Learning for Online Scheduling with Immediate Decision
2025
Optimal Algorithm for Max-Min Fair Bandit
Multi-player Multi-armed Bandits with Delayed Feedback
A Survey on Bandit Learning in Matching Markets
2024
Improved Analysis for Bandit Learning in Matching Markets
Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship
2022
Bandit Learning in Many-to-One Matching Markets
Contact
wangzilong [at] sjtu.edu.cn
John Hopcroft Center, Shanghai Jiao Tong University
Shanghai, China