Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Defu Lian
Observed name:
Lian, Defu
Institutions:
University of Science and Technology of China,
Hong Kong Baptist University
Observed institutions:
University of Science and Technology of China,
Hong Kong Baptist University
OpenAlex ID:
A5123683561
On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning
2026
·
Li, Zhaoyi
, Xi, Xiangyu
, et al.
·
arXiv (Cornell University)
·
3
PDF
Efficient and Stable Reinforcement Learning for Diffusion Language Models
2026
·
Liu, Jiawei
, Wang, Xiting
, et al.
·
arXiv (Cornell University)
·
3
PDF
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
2026
·
Jin, Haoran
, Wang, Xiting
, et al.
·
arXiv (Cornell University)
·
2
PDF
Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
2026
·
Li, Zhaoyi
, Li, Jiatong
, et al.
·
arXiv (Cornell University)
·
1
PDF
Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement
2026
·
Wu, Chenwang
, Cheung, Yiu-ming
, et al.
·
arXiv (Cornell University)
PDF
Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
2026
·
Wu, Chenwang
, Cheung, Yiuming
, et al.
·
arXiv (Cornell University)
PDF
Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection
2026
·
Wu, Chenwang
, Cheung, Yiu-ming
, et al.
·
arXiv (Cornell University)
PDF
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
2026
·
Yang, Wei
, Xie, Hong
, et al.
·
arXiv (Cornell University)
PDF
ChemEval2: A Diagnostic Benchmark for Evaluating Tool-Integrated Reasoning in Chemistry
2026
·
Yuqing Huang
, Chuang Tang
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Show more works
View as search
Works count:
15
Citation count:
9
H-index:
2
I10-index:
Year
Topic
Type