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

Thong Nguyen

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×1AI×1

Frequent co-authors

Dong Le1×
Cong-Duy Nguyen1×
Anh Tuan Luu1×
Tri Cao1×
Yulin Chen1×
Hieu Cao1×

Research Timeline

2026
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

The paper proposes WARD, a robust and efficient defense model that secures web agents against prompt injection attacks embedded in web content, achieving high recall and low false positives even against adaptive attacks.

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention

The paper introduces Curvature-Conditioned Query (CCQ), a novel read-time contraction mechanism that improves linear attention's performance on long-context and retrieval tasks by incorporating the geometry of the softmax function.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.LGRecentMay 31, 2026

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention

Dong Le, Thong Nguyen, Cong-Duy Nguyen, Anh Tuan Luu

The paper introduces Curvature-Conditioned Query (CCQ), a novel read-time contraction mechanism that improves linear attention's performance on long-context and retrieval tasks by incorporating the ge…

View →
cs.CRcs.AIRecentMay 14, 2026

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

Tri Cao, Yulin Chen, Hieu Cao, Yibo Li +7 more

The paper proposes WARD, a robust and efficient defense model that secures web agents against prompt injection attacks embedded in web content, achieving high recall and low false positives even again…

View →