Zhiyuan Fan
Scholar

Zhiyuan Fan

Google Scholar ID: vTOsT_MAAAAJ
PhD Student, MIT
reinforcement learningcomputational game theory
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
90
 
H-index
4
 
i10-index
2
 
Publications
9
 
Co-authors
6
list available
Contact
CVOpen ↗GitHubOpen ↗
Publications
26 items
GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
2026
Cited
0
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
2026
Cited
0
Toward Scalable Terminal Task Synthesis via Skill Graphs
2026
Cited
0
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
2026
Cited
0
Online Learning and Equilibrium Computation with Ranking Feedback
2026
Cited
0
Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
2026
Cited
0
Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?
2026
Cited
0
Empowering Reliable Visual-Centric Instruction Following in MLLMs
arXiv.org · 2026
Cited
1
Resume (English only)
Education
  • Currently a third-year Ph.D. student in computer science at MIT; previously graduated from Yao Class, Tsinghua University.
Background
  • Research interest: Theoretical machine learning and practical algorithms; graduated from Yao Class at Tsinghua University.
Co-authors
6 total
Jian Li
Jian Li
Professor, Tsinghua University
Quanquan Gu
Quanquan Gu
Associate Professor of Computer Science, UCLA
Weitong Zhang
Weitong Zhang
Assistant Professor, SDSS, UNC Chapel Hill
Jiafan He
Jiafan He
PhD student, Department of Computer Science, UCLA
Gabriele Farina
Gabriele Farina
Assistant Professor of Computer Science, MIT
Arnab Maiti
Arnab Maiti
PhD student ,CSE, University of Washington