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

Nowfel Mashnoor

3 indexed papers

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

Publications per year

3
26

Top categories

Architecture×3Crypto×2Prog. Lang.×1ML×1Logic×1

Frequent co-authors

Kimia Azar3×
Hadi Kamali3×
Mohammad Akyash1×
Mahshid Rezakhani1×

Research Timeline

2026
From Language to Logic: Bridging LLMs & Formal Representations for RTL Assertion Generation

The paper introduces ProofLoop, a novel ReAct agent that uses a solver-in-the-loop approach to automatically generate and formally verify SystemVerilog Assertions (SVA) from natural language specifications, achieving high levels of functional correctness.

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation

SafeTune is a framework that enhances the robustness of LLMs fine-tuned for RTL code generation by detecting and mitigating data poisoning attacks, particularly those aiming to insert hardware Trojans.

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

The paper introduces CASS-RTL, a novel, model-agnostic framework that enhances the functional correctness of Large Language Models (LLMs) generating Register-Transfer Level (RTL) code by leveraging the model's internal attention mechanisms.

Highlighted terms show continued research focus across papers

Papers

cs.PLcs.ARcs.LGRecentJun 4, 2026

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

The paper introduces CASS-RTL, a novel, model-agnostic framework that enhances the functional correctness of Large Language Models (LLMs) generating Register-Transfer Level (RTL) code by leveraging th…

View →
cs.CRcs.ARRecentApr 29, 2026

SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation

Mahshid Rezakhani, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

SafeTune is a framework that enhances the robustness of LLMs fine-tuned for RTL code generation by detecting and mitigating data poisoning attacks, particularly those aiming to insert hardware Trojans…

View →
cs.CRcs.ARcs.LORecentApr 25, 2026

From Language to Logic: Bridging LLMs & Formal Representations for RTL Assertion Generation

Nowfel Mashnoor, Hadi Kamali, Kimia Azar

The paper introduces ProofLoop, a novel ReAct agent that uses a solver-in-the-loop approach to automatically generate and formally verify SystemVerilog Assertions (SVA) from natural language specifica…

View →