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

Zheng Fang

2 indexed papers

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

Publications per year

2
26

Top categories

Econometrics×1Stats Theory×1Stats Method.×1Stats ML×1Crypto×1AI×1NLP×1ML×1

Frequent co-authors

Qihui Chen1×
Ka Yan Cheng1×
Xiaosen Wang1×
Shenyi Zhang1×
Shaokang Wang1×
Zhijin Ge1×

Research Timeline

2026
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization

The paper introduces Token-Aware Gradient Optimization (TAGO), demonstrating that sparse optimization focusing only on high-gradient audio tokens is sufficient for effective jailbreaking of audio language models, making dense updates redundant.

Debiased Machine Learning: Identification, Estimation, and Shape Constraints

This paper develops a framework for identifying and estimating parameters of interest in automatic debiased machine learning using a Riesz representer, which is identified when it uniquely optimizes a quadratic functional.

Highlighted terms show continued research focus across papers

Papers

econ.EMmath.STstat.METheoreticalRecentJul 27, 2026

Debiased Machine Learning: Identification, Estimation, and Shape Constraints

Qihui Chen, Ka Yan Cheng, Zheng Fang

This paper develops a framework for identifying and estimating parameters of interest in automatic debiased machine learning using a Riesz representer, which is identified when it uniquely optimizes a…

View →
cs.CRcs.AIcs.CLRecent
May 6, 2026

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization

Zheng Fang, Xiaosen Wang, Shenyi Zhang, Shaokang Wang +1 more

The paper introduces Token-Aware Gradient Optimization (TAGO), demonstrating that sparse optimization focusing only on high-gradient audio tokens is sufficient for effective jailbreaking of audio lang…

View →