MS
Minghao Shao
cs.AIcs.CRcs.LGcs.ARcs.SEcs.CLcs.MAcs.PLquant-phcs.CY
On Valency
published · living versionsW_rrgufdc3·v1 · currentpublished
ROSTrans: Empirically Benchmarking LLMs for ROS1-to-ROS2 Migration
with Yichen Zhao, Zhuoyan Yu, Yijun Shen, Boyuan Chen +2
1 version
W_75uwn8ew·v1published
Preprints & journals
32 papers in the corpus · 2024–2026QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code2610.13811v1 · Meriem Terki, Nouhaila Innan, Minghao Shao et al.2026 · 0 citationsarXiv
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio2610.07005v1 · Boyuan Chen, Minseok Kim, Sohaila Abdulsattar et al.2026 · 0 citationsarXiv
Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks2610.07009v1 · Boyuan Chen, Yehia Dawoud, Hailemariam Mersha et al.2026 · 0 citationsarXiv
HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization2609.09835v1 · Jianzhi Shen, Keyu Mao, Minghao Shao et al.2026 · 0 citationsarXiv
How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation2608.26237v1 · Kimberly Milner, Minghao Shao, Nanda Rani et al.2026 · 0 citationsarXiv
FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?2608.00909v1 · Weimin Fu, Hejia Zhang, Minghao Shao et al.2026 · 0 citationsarXiv
VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation2606.13735v1 · Yijun Shen, Minghao Shao, Yichen Zhao et al.2026 · 0 citationsarXiv
QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy2606.04620v1 · Pasindu Wickramasinghe, Achyuta Muthuvelan, Rachmad Vidya Wicaksana Putra et al.2026 · 0 citationsarXiv
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation2605.25572v2 · Minghao Shao, Nouhaila Innan, Hariharan Janardhanan et al.2026 · 0 citationsarXiv
Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models2604.21952v1 · Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif et al.2026 · 0 citationsarXiv
RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs2604.17948v2 · Parteek Jamwal, Minghao Shao, Boyuan Chen et al.2026 · 0 citationsarXiv
HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking2604.17093v1 · Zeng Wang, Minghao Shao, Weimin Fu et al.2026 · 1 citationarXiv
From Natural Language to Silicon: The Representation Bottleneck in LLM Hardware Design2604.17097v1 · Weimin Fu, Zeng Wang, Minghao Shao et al.2026 · 0 citationsarXiv
Configuration Over Selection: Hyperparameter Sensitivity Exceeds Model Differences in Open-Source LLMs for RTL Generation2604.17102v1 · Minghao Shao, Zeng Wang, Weimin Fu et al.2026 · 0 citationsarXiv
AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes2603.21551v2 · Haoran Xi, Minghao Shao, Kimberly Milner et al.2026 · 0 citationsarXiv
Synthesis-in-the-Loop Evaluation of LLMs for RTL Generation: Quality, Reliability, and Failure Modes2603.11287v2 · Weimin Fu, Zeng Wang, Minghao Shao et al.2026 · 0 citationsarXiv
CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking2602.08023v3 · Nanda Rani, Kimberly Milner, Minghao Shao et al.2026 · 0 citationsarXiv
TrojanLoC: LLM-based Framework for RTL Trojan Localization2512.00591v1 · Weihua Xiao, Zeng Wang, Minghao Shao et al.2025 · 0 citationsarXiv
VeriDispatcher: Multi-Model Dispatching through Pre-Inference Difficulty Prediction for RTL Generation Optimization2511.22749v1 · Zeng Wang, Weihua Xiao, Minghao Shao et al.2025 · 0 citationsarXiv
NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration2512.00119v1 · Zeng Wang, Minghao Shao, Akashdeep Saha et al.2025 · 0 citationsarXiv
From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization2510.02389v3 · Haoran Xi, Minghao Shao, Brendan Dolan-Gavitt et al.2025 · 0 citationsarXiv
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark2508.05674v2 · Minghao Shao, Nanda Rani, Kimberly Milner et al.2025 · 2 citationsarXiv
MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs2506.22557v2 · Boyuan Chen, Minghao Shao, Abdul Basit et al.2025 · 0 citationsarXiv
QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges2506.20008v2 · Abdul Basit, Minghao Shao, Muhammad Haider Asif et al.2025 · 3 citations2025 IEEE International Conference on Quantum Artificial Intelligence (QAI), Naples, Italy, 2025, pp. 316-322
SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design2506.02089v4 · Zeng Wang, Minghao Shao, Rupesh Karn et al.2025 · 5 citationsarXiv
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution2505.17107v1 · Minghao Shao, Haoran Xi, Nanda Rani et al.2025 · 2 citationsarXiv
A PennyLane-Centric Dataset to Enhance LLM-based Quantum Code Generation using RAG2503.02497v4 · Abdul Basit, Nouhaila Innan, Muhammad Haider Asif et al.2025 · 0 citations2026 International Joint Conference on Neural Networks (IJCNN), Maastricht, Netherlands, 2026, pp. 1-8
D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security2502.10931v2 · Meet Udeshi, Minghao Shao, Haoran Xi et al.2025 · 1 citationarXiv
Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges2412.03220v1 · Minghao Shao, Abdul Basit, Ramesh Karri et al.2024 · 96 citationsarXiv
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities2409.16165v3 · Talor Abramovich, Meet Udeshi, Minghao Shao et al.2024 · 1 citationarXiv
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security2406.05590v3 · Minghao Shao, Sofija Jancheska, Meet Udeshi et al.2024 · 18 citationsarXiv
An Empirical Evaluation of LLMs for Solving Offensive Security Challenges2402.11814v1 · Minghao Shao, Boyuan Chen, Sofija Jancheska et al.2024 · 10 citationsarXiv
Career total: 44 works. 32 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.