Author

Yuqian Fu

Observed name: Fu, Yuqian

Institutions: Chinese Academy of Sciences, Fudan University, Institute of Automation, Artificial Intelligence in Medicine (Canada), University of Chinese Academy of Sciences, King Abdullah University of Science and Technology

Observed institutions: Chinese Academy of Sciences, Fudan University, Institute of Automation, Artificial Intelligence in Medicine (Canada), University of Chinese Academy of Sciences, King Abdullah University of Science and Technology

OpenAlex ID: A5130794549

Are Full Rollouts Necessary for On-Policy Distillation?

2026 · Zhang, Yaocheng, Chai, Jiajun, et al. · arXiv (Cornell University)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

2026 · Fu, Yuqian, Huang, Haohuan, et al. · arXiv (Cornell University)

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety–Utility Balancing

2026 · Zhijie Zheng, Yu Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 3

Citation count:

H-index:

I10-index: