Get started
Author

David Lo

Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild
2026 · Liu, Yue, Widyasari, Ratnadira, et al. · arXiv (Cornell University) · 2
PDF
Seeing Is Coding: On the Effectiveness of Vision Language Models in Code Understanding
2026 · Yuling Shi, Chaoxiang Xie, et al. · Proceedings of the ACM on software engineering. · 1
Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
2026 · Li, Yikun, Zhang, Ting, et al. · arXiv (Cornell University) · 1
PDF
ExploreRepair: Evidence-Specialized Agents for Vulnerability Repair under Information Constraints
2026 · Tran, Duc Manh, Widyasari, Ratnadira, et al. · arXiv (Cornell University)
PDF
Pairing Matters: Performance, Failures, and Efficiency in Lightweight Coding Agents
2026 · Zhao, Lu, Poskitt, Christopher M., et al. · arXiv (Cornell University)
PDF
Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup
2026 · Shi, Yuling, Zhong, Mingchu, et al. · arXiv (Cornell University)
PDF
RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation
2026 · Chen, Yuchen, Cheng, Wei, et al. · arXiv (Cornell University)
PDF
Teaching Code Agents to Ask Without Leaking Private Code
2026 · Jiang, Wenjia, Shi, Jieke, et al. · arXiv (Cornell University)
PDF
SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation
2026 · Han, Ruidong, Sun, Zhensu, et al. · arXiv (Cornell University)
PDF
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
2026 · Minn, Wei, Sun, Zhensu, et al. · arXiv (Cornell University)
PDF
Multi-level Code Optimization via Mixture of Prompts
2026 · Yun Peng, Jun Wan, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
We Must Have Missed This Comment: Detecting and Repairing Stale Function References in Linux Kernel Comments
2026 · Kexin Sun, Yunbo Lyu, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
PDF
AgentExecutor: Partial Code Execution via Agentic Context Generation
2026 · Junkai Chen, Chengran Yang, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
How Reasoning Shapes Social Bias in LLM-Generated Code?
2026 · Weifeng Sun, Jieke Shi, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
PDF
Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering
2026 · Xiuwei Shang, Li Hu, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
PDF
AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
2026 · Gou Tan, Zhensu Sun, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
2026 · Zhihao Lin, Junhua Zhu, et al. · Proceedings of the ACM on software engineering.
PDF
Understanding and Improving Model Editing for Secure Code Generation
2026 · Weifeng Sun, Quanjun Zhang, et al. · Proceedings of the ACM on software engineering.
PDF
Aletheia: Permission-Minimality Testing for Coding-Agent Rules
2026 · Shi, Jieke, Chen, Yuchen, et al. · arXiv (Cornell University)
PDF
Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail
2026 · Tan, Gou, Chen, Pengfei, et al. · arXiv (Cornell University)
PDF
Path2Spec: Path-Aware Specification Generation via Large Language Models
2026 · Huang, Dan, Sun, Zhensu, et al. · arXiv (Cornell University)
PDF
VulContextBench: A Benchmark for Security Context Retrieval in Coding Agents
2026 · Li, Yikun, Jiang, Jinfeng, et al. · arXiv (Cornell University)
PDF
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
2026 · Shi, Yuling, Sun, Zhensu, et al. · arXiv (Cornell University)
PDF
A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents
2026 · Zhou, Xin, Chong, Chun Yong, et al. · arXiv (Cornell University)
PDF
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
2026 · Wang, Chenyu, Lyu, Yunbo, et al. · arXiv (Cornell University)
PDF
Works count: 48
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type