Scholar
Yuxuan Tong
Google Scholar ID: 6E0O8LcAAAAJ
Undergraduate at Tsinghua University
Citations & Impact
Citations
1,614
H-index
4
i10-index
4
Publications
4
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Co-first author and infrastructure lead (†) of 'DAPO: an Open-Source LLM Reinforcement Learning System at Scale' (preprint, under review)
- Co-first author of 'Demystifying Long Chain-of-Thought Reasoning in LLMs', accepted by ICML 2025 and awarded Best Paper at ICLR 2025 FM-Wild Workshop
- First author of 'DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving', accepted by NeurIPS 2024
- Co-author of 'ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation', accepted by NeurIPS 2023
- Recipient of Tsinghua University Research Scholarship (2023)
- Core contributor and maintainer of verl, a large-scale reinforcement learning library for LLMs
