Scholar
Jiarui Yao
Google Scholar ID: 84fexSEAAAAJ
CS, UIUC
Citations & Impact
Citations
130
H-index
5
i10-index
3
Publications
11
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- Released GVM - Gradient Variance Minimization, a framework to improve data sampling efficiency in LLMs math reasoning.
- Wrote a report analyzing what makes GRPO 'stand out' for math reasoning, with some understanding and ablation studies to compare different algorithms for LLMs reasoning training.
- Released FANS - Formal Answer Selection for Natural Language Reasoning Using Lean4, enhancing test-time math answer selection using formal language.
- Published the paper 'Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL'.
- Published the paper 'A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce'.
- Published the paper 'FANS – Formal Answer Selection for Natural Language Math Reasoning Using Lean4'.
Research Experience
- Started the PhD journey in the CS School of UIUC in August 2024.
Education
- First-year CS PhD student in the Siebel School of Computing and Data Science, University of Illinois, Urbana-Champaign (UIUC), supervised by Prof. Tong Zhang; Bachelor of Engineering from Yao Class, Tsinghua University.
Background
- Main research interests focus on reinforcement learning, large language models, especially autonomous agents learning, model reasoning, and interdisciplinary fields.
Miscellany
- Blog includes a Japan travel journal with photo collections.
