Xinye Zhao

Xinye Zhao

Ph.D. student in Computer Science and Engineering at the University of Notre Dame, with research interests in AI for Software Engineering (AI4SE), Software Engineering Security, and Systems for Machine Learning.

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

STRATA: A Security Tactic-Aware Framework for LLM-Based Vulnerability Repair figure

STRATA: A Security Tactic-Aware Framework for LLM-Based Vulnerability Repair

Mohammed Latif Siddiq, Xinye Zhao, Joanna Cecilia da Silva Santos

[PREPRINT] SSRN, 2026

A static-analysis-guided LLM pipeline for security tactic-aware vulnerability repair in Java programs.

Preprint |

Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub figure

Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub

Mohammed Latif Siddiq, Xinye Zhao, Vinicius Carvalho Lopes, Beatrice Casey, Joanna C. S. Santos

[PREPRINT] arXiv, 2026

An empirical study of security-related agentic pull requests on GitHub.

scDisInFact: Disentangled Learning for the Integration and Prediction of Multi-Batch, Multi-Condition Single-Cell RNA-Sequencing Data figure

scDisInFact: Disentangled Learning for the Integration and Prediction of Multi-Batch, Multi-Condition Single-Cell RNA-Sequencing Data

Ziqi Zhang, Xinye Zhao, Mehak Bindra, Peng Qiu, Xiuwei Zhang

[PUBLISHED IN] Nature Communications, 2024

Disentangled learning for integration and prediction across multi-batch, multi-condition single-cell RNA-sequencing data.

scMODD: A model-driven algorithm for doublet identification in single-cell RNA-sequencing data figure

scMODD: A model-driven algorithm for doublet identification in single-cell RNA-sequencing data

Xinye Zhao, Alexander Du, Peng Qiu

[PUBLISHED IN] Frontiers in Systems Biology, 2023

A model-driven algorithm for doublet identification in single-cell RNA-sequencing data.

Conference Papers

TriVul: Improving Precision of Static Vulnerability Detection through Multi-Agent Reasoning figure

TriVul: Improving Precision of Static Vulnerability Detection through Multi-Agent Reasoning

X. Zhao, Joanna C. S. Santos

[ACCEPTED TO] SAS'26: 33rd Static Analysis Symposium, 2026

A multi-agent assisted static analysis framework for Java vulnerability detection that improves precision through stage-specific reasoning.

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching figure

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching

Xinye Zhao, Spyridon Mastorakis

[PUBLISHED IN] IJCNLP 2025, 2025

Efficient KVCache sharing for semantically similar prompts via token-level LSH matching.

Workshop Papers