Scholar
Yuyang Ding
Google Scholar ID: 1E4sN7sAAAAJ
Soochow University
Citations & Impact
Citations
85
H-index
4
i10-index
4
Publications
9
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- NeurIPS 2025: FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
- ACL 2025: SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
- IEEE TKDE: DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations
- ACL 2024: ScaleQuest: Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch
- COLING 2022: GNER: Rethinking Negative Instances for Generative Named Entity Recognition
- SCIS (CCF-A): SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training (*equal contribution)
- EMNLP 2023: OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch (*equal contribution)
- EMNLP 2022: CMD: a framework for Context-aware Model self-Detoxification
- CCF Elite Collegiate Award
- Gold Medal, ICPC National Invitational Programming Contest
- Silver Medal, ICPC Asia-East Continent Final Contest (EC-Final)
Background
- Third-year Ph.D. student at the Institute of Artificial Intelligence, Soochow University
- Research focuses on LLM Reasoning
- Particular interests in reinforcement learning, test-time scaling, and robust learning
- Currently a research intern at Seed-Infrastructures, ByteDance, contributing to verl, an RL framework for LLMs
- Research emphasizes joint optimization of algorithms and infrastructure for scalable and efficient reinforcement learning
Co-authors