Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Can Jin
Observed name:
Jin, Can
Institution:
Rutgers, The State University of New Jersey
Observed institution:
Rutgers, The State University of New Jersey
OpenAlex ID:
A5135950347
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
2026
·
Zhou, Yang
, Jin, Can
, et al.
·
arXiv (Cornell University)
·
5
PDF
Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
2026
·
Jin, Can
, Li, Jiakang
, et al.
·
arXiv (Cornell University)
·
4
PDF
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
2026
·
Jiakang Li
, Guanyu Zhu
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
4
PDF
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
2026
·
Zhou, Yang
, Dong, Zihan
, et al.
·
arXiv (Cornell University)
·
3
PDF
Show more works
View as search
Works count:
4
Citation count:
16
H-index:
3
I10-index:
Year
Topic
Type
