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

Syed Nazmus Sakib

3 indexed papers

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

Publications per year

3
26

Top categories

AI×3Crypto×2Vision×1

Frequent co-authors

Nafiul Haque3×
Shifat E Arman3×
Shahrear Bin Amin2×

Research Timeline

2026
PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by explicitly enforcing physical laws and geometric constraints, significantly outperforming current state-of-the-art models.

The Surface You Test Is Not the Surface That Breaks

The vulnerability of LLM agents to prompt injection depends not on the specific channel (tool output vs. tool description) but on the interaction between the model and the surface itself.

The Surface You Test Is Not the Surface That Breaks

The vulnerability of LLM agents to prompt injection depends not on the specific channel (tool output vs. tool description) but on the interaction between the model and the surface.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CVRecentMay 28, 2026

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

Nafiul Haque, Syed Nazmus Sakib, Shifat E Arman

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by explicitly enforcing physical laws and geometric constraints, significantly outperforming c…

View →
cs.CRcs.AIRecentMay 28, 2026

The Surface You Test Is Not the Surface That Breaks

Shifat E Arman, Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin

The vulnerability of LLM agents to prompt injection depends not on the specific channel (tool output vs. tool description) but on the interaction between the model and the surface itself.

View →
cs.CRcs.AIRecentMay 28, 2026

The Surface You Test Is Not the Surface That Breaks

Shifat E Arman, Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin

The vulnerability of LLM agents to prompt injection depends not on the specific channel (tool output vs. tool description) but on the interaction between the model and the surface.

View →