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

Li Wang

7 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

7
26

Top categories

AI×5Crypto×3Audio and Speech Processing×1Software Eng.×1ML×1

Frequent co-authors

Zhexin Hu2×
Xiaohan Wang2×
Jiajun Chai2×
Xiaojun Guo2×
Wei Lin2×
Guojun Yin2×

Research Timeline

2026
Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models

The paper introduces EvoJail, an automated multi-objective evolutionary framework that systematically discovers diverse and effective long-tail jailbreak attacks against LLMs by optimizing for attack effectiveness and minimizing output perplexity.

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned parameter updates in shared layers.

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compression with Hindsight Response Replay.

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compression with Hindsight Response Replay.

HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection

This paper introduces a new benchmark for detecting AI-generated code in industry codebases.

RealComm: Benchmarking and Adapting Audio Deepfake Detection over Real Communication Channels

This paper introduces RealComm, a dataset and augmentation pipeline for evaluating the effects of real call transmission on audio deepfake detection.

Highlighted terms show continued research focus across papers

Papers

eess.ASEmpiricalRecentOct 20, 2026

RealComm: Benchmarking and Adapting Audio Deepfake Detection over Real Communication Channels

Li Wang, Jindong Wang, Wan Lin, Kunyu Feng +8 more

This paper introduces RealComm, a dataset and augmentation pipeline for evaluating the effects of real call transmission on audio deepfake detection.

View →
cs.SEcs.AIEmpiricalRecent
Jun 10, 2026

HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection

Luke Patterson, Li Wang, Adam Faulkner

This paper introduces a new benchmark for detecting AI-generated code in industry codebases.

View →
cs.AIRecentMay 27, 2026

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

Zhexin Hu, Li Wang, Xiaohan Wang, Jiajun Chai +3 more

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

View →
cs.AIRecentMay 27, 2026

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

Zhexin Hu, Li Wang, Xiaohan Wang, Jiajun Chai +3 more

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

View →
cs.CRMay 14, 2026

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models

Xiangtao Meng, Wenyu Chen, Chuanchao Zang, Xinyu Gao +4 more

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned param…

View →
cs.CRcs.AIcs.LGMar 24, 2026

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Wenyu Chen, Xiangtao Meng, Chuanchao Zang, Li Wang +5 more

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

View →
cs.CRcs.AIMar 20, 2026

Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models

Wenjing Hong, Zhonghua Rong, Li Wang, Feng Chang +4 more

The paper introduces EvoJail, an automated multi-objective evolutionary framework that systematically discovers diverse and effective long-tail jailbreak attacks against LLMs by optimizing for attack…

View →