Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Lin Liu

Lin Liu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Stats Theory×1Econometrics×1Stats ML×1Crypto×1AI×1

Frequent co-authors

Rajarshi Mukherjee1×
James M Robins1×
Wenqi Chen1×
Ziyan Zhang1×
Bing Wang1×
Hengheng Zhang1×

Research Timeline

2026
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

The paper introduces Tree-like Self-Play (TSP), a novel framework that treats secure code generation as a fine-grained decision process, significantly improving LLM security by forcing the model to self-correct localized vulnerabilities.

On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models

This paper shows that the Double Machine Learning (DML) estimator is asymptotically inadmissible for certain functionals under the Structure-agnostic (SA) model.

Highlighted terms show continued research focus across papers

Papers

math.STecon.EMstat.MLTheoreticalRecentJun 21, 2026

On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models

Lin Liu, Rajarshi Mukherjee, James M Robins

This paper shows that the Double Machine Learning (DML) estimator is asymptotically inadmissible for certain functionals under the Structure-agnostic (SA) model.

View →
cs.CRcs.AIRecent
Jun 2, 2026

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

Wenqi Chen, Ziyan Zhang, Bing Wang, Lin Liu +2 more

The paper introduces Tree-like Self-Play (TSP), a novel framework that treats secure code generation as a fine-grained decision process, significantly improving LLM security by forcing the model to se…

View →