Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Yuran Wang
Observed name:
Wang, Yuran
Institutions:
Fudan University,
Honor Device (China)
Observed institutions:
Fudan University,
Honor Device (China)
OpenAlex ID:
A5125220225
DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
2026
·
Zhu, Dingwei
, Xi, Zhiheng
, et al.
·
arXiv (Cornell University)
PDF
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
2026
·
Dingwei Zhu
, Shihan Dou
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
Show more works
View as search
Works count:
2
Citation count:
H-index:
I10-index:
Year
Topic
Type
