Picture for Michele Tufano

Michele Tufano

Agentic Bug Reproduction for Effective Automated Program Repair at Google

Add code
Feb 03, 2025
Figure 1 for Agentic Bug Reproduction for Effective Automated Program Repair at Google
Figure 2 for Agentic Bug Reproduction for Effective Automated Program Repair at Google
Figure 3 for Agentic Bug Reproduction for Effective Automated Program Repair at Google
Figure 4 for Agentic Bug Reproduction for Effective Automated Program Repair at Google
Viaarxiv icon

Evaluating Agent-based Program Repair at Google

Add code
Jan 13, 2025
Viaarxiv icon

AutoDev: Automated AI-Driven Development

Add code
Mar 13, 2024
Viaarxiv icon

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Add code
Feb 22, 2024
Viaarxiv icon

Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation

Add code
Oct 03, 2023
Viaarxiv icon

Predicting Code Coverage without Execution

Add code
Jul 25, 2023
Figure 1 for Predicting Code Coverage without Execution
Figure 2 for Predicting Code Coverage without Execution
Figure 3 for Predicting Code Coverage without Execution
Figure 4 for Predicting Code Coverage without Execution
Viaarxiv icon

An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation

Add code
Jan 03, 2023
Figure 1 for An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation
Figure 2 for An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation
Figure 3 for An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation
Figure 4 for An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation
Viaarxiv icon

Exploring and Evaluating Personalized Models for Code Generation

Add code
Aug 29, 2022
Figure 1 for Exploring and Evaluating Personalized Models for Code Generation
Figure 2 for Exploring and Evaluating Personalized Models for Code Generation
Figure 3 for Exploring and Evaluating Personalized Models for Code Generation
Figure 4 for Exploring and Evaluating Personalized Models for Code Generation
Viaarxiv icon

Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy

Add code
Sep 17, 2021
Figure 1 for Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Figure 2 for Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Figure 3 for Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Figure 4 for Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Viaarxiv icon

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

Add code
Feb 09, 2021
Figure 1 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 2 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 3 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Figure 4 for CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Viaarxiv icon