Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Kaiyuan Liu
Observed names:
Liu, Kaiyuan,
liu, kaiyuan
Institutions:
Jilin University,
University of Washington,
Harbin Institute of Technology,
Peng Cheng Laboratory,
Meituan (China),
Zhejiang University
show all 6
Observed institutions:
Jilin University,
University of Washington,
Harbin Institute of Technology,
Peng Cheng Laboratory,
Meituan (China),
Zhejiang University
show all 6
OpenAlex ID:
A5136102229
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
2026
·
Liu, Kaiyuan
, Zhuang, Ziyuan
, et al.
·
arXiv (Cornell University)
·
16
PDF
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
2026
·
Wang, Bing
, Yan, Shaotian
, et al.
·
arXiv (Cornell University)
·
13
PDF
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
2026
·
Bai, Yang
, Liu, Kaiyuan
, et al.
·
arXiv (Cornell University)
·
6
PDF
CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
2026
·
Yexing Du
, Kaiyuan Liu
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
·
5
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
2026
·
He, Runyuan
, Mang, Qiuyang
, et al.
·
arXiv (Cornell University)
·
4
PDF
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
2026
·
Zhou, Shang
, Chai, Wenhao
, et al.
·
arXiv (Cornell University)
·
3
PDF
RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges
2026
·
Liu, Kaiyuan
, Zhuang, Ziyuan
, et al.
·
arXiv (Cornell University)
·
2
PDF
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
2026
·
Wang, Bing
, Miao, Rui
, et al.
·
arXiv (Cornell University)
·
1
PDF
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders
2026
·
Du, Yexing
, Liu, Kaiyuan
, et al.
·
arXiv (Cornell University)
PDF
Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translation
2026
·
Du, Yexing
, Liu, Kaiyuan
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
10
Citation count:
50
H-index:
4
I10-index:
2
Year
Topic
Type