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

Peng Fu

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1ML×1Crypto×1Stats ML×1

Frequent co-authors

Shihao Rao1×
Liang Li1×
Jiapeng Liu1×
Tong Lin1×
Bing Li1×
Xiyan Gao1×

Research Timeline

2026
Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory

This paper theoretically analyzes Continuous Adversarial Training (CAT) for LLMs using In-context Learning (ICL) theory, proving that embedding space perturbations effectively enhance robustness against token-space jailbreaks and proposing a singular value regularization method for improvement.

What to Format and How: A Benchmark and Workflow Approach for Document Formatting

The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target localization from modification execution.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

What to Format and How: A Benchmark and Workflow Approach for Document Formatting

Shihao Rao, Liang Li, Jiapeng Liu, Tong Lin +5 more

The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…

View →
cs.LGcs.CRstat.MLRecentApr 14, 2026

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory

Shaopeng Fu, Di Wang

This paper theoretically analyzes Continuous Adversarial Training (CAT) for LLMs using In-context Learning (ICL) theory, proving that embedding space perturbations effectively enhance robustness again…

View →