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

Liang Wang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×2Crypto×2NLP×1Emerging Tech×1Sound×1Software Eng.×1

Frequent co-authors

Liuji Chen1×
Dianxing Tang1×
Xing Shi1×
Dingshuo Chen1×
Qiang Liu1×
Shu Wu1×

Research Timeline

2026
Detecting Protracted Vulnerabilities in Open Source Projects

The paper analyzes protracted vulnerabilities (PCVEs) in open-source projects and proposes DeeptraVul, an enhanced detection approach that significantly improves vulnerability coverage by integrating multiple development artifacts and an LLM.

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright protection without requiring per-LoRA retraining.

GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identification regardless of geometric variations.

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

Liuji Chen, Dianxing Tang, Xing Shi, Dingshuo Chen +3 more

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

View →
cs.CLRecentJun 1, 2026

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization

Liang Wang, Xinyi Mou, Xiaoyou Liu, Tiannan Wang +2 more

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels…

View →
cs.ETcs.AIcs.SDRecentMay 29, 2026

GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement

Zhiwei Chen, Yijie Li, Yimo Zhang, Shiyun Shao +8 more

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identif…

View →
cs.CRRecentMay 28, 2026

LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models

Yaopeng Wang, Qingliang Wang, Zhibo Wang, Huiyu Xu +4 more

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright prot…

View →
cs.CRcs.SERecentMar 28, 2026

Detecting Protracted Vulnerabilities in Open Source Projects

Arjun Sridharkumar, Sara Al Hajj Ibrahim, Jiayuan Zhou, Yuliang Wang +3 more

The paper analyzes protracted vulnerabilities (PCVEs) in open-source projects and proposes DeeptraVul, an enhanced detection approach that significantly improves vulnerability coverage by integrating…

View →