Scholar
Yongding Tao
Google Scholar ID: RejcNLAAAAAJ
Peking University
Citations & Impact
Citations
39
H-index
3
i10-index
1
Publications
5
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Preprint: CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment (arXiv:25.10)
- Preprint: Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models (arXiv:25.10)
- Preprint: RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (arXiv:25.08)
- Conference Paper: FANformer: Improving Large Language Models Through Effective Periodicity Modeling (NeurIPS 2025)
- Conference Paper: FAN: Fourier Analysis Networks (NeurIPS 2025)
- Conference Paper: ROCODE: Integrating Backtracking Mechanism and Program Analysis in Large Language Models for Code Generation (ICSE 2025)
- Short Paper: A Novel Window-Interaction Module Based on W-MSA (Tiny Paper at ICLR 2024)
Background
- First year Ph.D. student in the School of Computer Science, Peking University, with research interests mainly focused on LLM Reasoning, Foundation Model Architecture and AI for Software Engineering (AI4SE).
