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

Linkang Du

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×2AI×2Crypto×2ML×2

Frequent co-authors

Peiqi Jia1×
Haonan Jia1×
Ziqi Miao1×
Yuntao Wang1×
Zhou Su1×
Bing Liu1×

Research Timeline

2026
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

This paper systematically investigates how various plasticity interventions affect the vulnerability of deep reinforcement learning agents to backdoor attacks, finding that most interventions mitigate threats while one specific intervention exacerbates them.

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models, and generated content.

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

This paper introduces explicit personality conditioning and evaluation framework for Multimodal Large Language Models.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIEmpiricalRecentJun 9, 2026

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

Peiqi Jia, Haonan Jia, Ziqi Miao, Linkang Du +2 more

This paper introduces explicit personality conditioning and evaluation framework for Multimodal Large Language Models.

View →
cs.CRcs.CLcs.LGRecent
May 28, 2026

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

Bing Liu, Shunping Wang, Yufan Zhu, Xinyi Yu +4 more

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

View →
cs.LGcs.AIcs.CRMay 14, 2026

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

Oubo Ma, Ruixiao Lin, Yang Dai, Jiahao Chen +3 more

This paper systematically investigates how various plasticity interventions affect the vulnerability of deep reinforcement learning agents to backdoor attacks, finding that most interventions mitigate…

View →