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

Ziwei Wang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2ML×2Signal Processing×1Sound×1Audio and Speech Processing×1Robotics×1Crypto×1

Frequent co-authors

Xingyi He1×
Tianwang Jia1×
Hongbin Wang1×
Dongrui Wu1×
Haoyuan Deng1×
Yitong Gao1×

Research Timeline

2026
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling

The paper introduces Babel, an efficient black-box attack framework that systematically exploits intrinsic safety gaps in LLMs by optimizing text obfuscation sampling, achieving state-of-the-art jailbreak success rates on commercial models.

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

UniIntervene proposes an agentic intervention model for human-in-the-loop reinforcement learning to reduce human interventions and improve policy efficiency.

FAConformer: Frequency-Aware Convolutional Transformer for Auditory Attention Decoding

This paper proposes FAConformer, a framework for auditory attention decoding using frequency-aware CNN-Transformer, which performs frequency-aware modeling and outperforms existing methods.

Highlighted terms show continued research focus across papers

Papers

eess.SPcs.AIcs.LGEmpiricalRecentJun 12, 2026

FAConformer: Frequency-Aware Convolutional Transformer for Auditory Attention Decoding

Ziwei Wang, Xingyi He, Tianwang Jia, Hongbin Wang +1 more

This paper proposes FAConformer, a framework for auditory attention decoding using frequency-aware CNN-Transformer, which performs frequency-aware modeling and outperforms existing methods.

View →
cs.ROcs.LGEmpirical
Recent
Jun 10, 2026

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

Haoyuan Deng, Yitong Gao, Yudong Lin, Haichao Liu +2 more

UniIntervene proposes an agentic intervention model for human-in-the-loop reinforcement learning to reduce human interventions and improve policy efficiency.

View →
cs.CRcs.AIMay 18, 2026

Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling

Ziwei Wang, Jing Chen, Ruichao Liang, Zhi Wang +5 more

The paper introduces Babel, an efficient black-box attack framework that systematically exploits intrinsic safety gaps in LLMs by optimizing text obfuscation sampling, achieving state-of-the-art jailb…

View →