• Ciao,
    I am .

  • "Read. Think. Create. Repeat."

About me

  • Bachelor’s and Master’s Degree
    in Computer Engineering
  • Research Internship
    in Generative AI
  • Ph.D. Degree
    in Computer Science


I am Luca Di Grazia and I am a PhD Candidate in Software Engineering in the Software Lab group at Stuttgart Universität, part of the alliance of leading German Technical Universities, advised by Prof. Michael Pradel. In 2019, I graduated in Computer Engineering (Embedded systems) at Politecnico di Torino with the thesis (published in PROTEINS): "A new method for protein characterization and classification using geometrical features for 3D face analysis: An example of tubulin structures", advised by Prof. Federica Marcolin and Prof. Jack A. Tuszynski.

My research in software engineering has been recognized with multiple awards and achievements. In 2023, my project on Generative AI won a Uber competition among 103 teams worldwide. In 2022, my paper on Python annotations obtained the important ACM SIGSOFT Distinguished Paper Award. Additionally, I was the second winner at the ACM Student Research Competition and won the first phase of the Gnome Challenge 2020. From 2016 to 2018, I received a generous scholarship to study computer engineering. Furthermore, I have published papers in international peer-reviewed conferences and journals. Currently, I serve as a reviewer for ACM TOSEM, which is widely recognized as one of the most prestigious journals in software engineering.

My work focuses on Generative AI (Uber research internship), Software Evolution and Mining Repositories (ESEC/FSE 2022, Distinguished Paper Award), Code Change Retrieval (IEEE TSE paper, ICSE 2022 SRC 2nd winner), Code Search (ACM CSUR paper), and more. Additionally, I have supervised a total of seven students, including projects on "Towards Automatically Repairing Errors in Python", "Testing FAISS indexing on DiffSearch", on "Improving the Recall of Searching for Code Changes", and more.

My complete CV and references are avaible on request. All opinions expressed in this website are my own and not of my employer. No information is gathered from you by this website.

Email

Latest News

07/2023: ASE! Our paper: “DiffSearch: A Scalable and Precise Search Engine for Code Changes” has been accepted for the Journal-first track at ASE 2023 in Luxembourg.

06/2023: Won a Uber competition on Generative AI for developer productivity among 103 teams worldwide.

05/2023: Generative AI at Uber! I am joining Uber for a research internship in Amsterdam for summer 2023.

04/2023: Dagstuhl Seminar! I was invited to the world’s leading researchers Dagstuhl Seminar about Code Search for spring 2024.

03/2023: I was invited by JetBrains in their Munich office to discuss our paper “DiffSearch: A Scalable and Precise Search Engine for Code Changes”.

02/2023: Start serving as a reviewer for the prestigious journal ACM Transactions on Software Engineering and Methodology (TOSEM).

12/2022: Distinguished Paper Award! Our paper “The Evolution of Type Annotations in Python: An Empirical Study” received an ACM SIGSOFT Distinguished Paper Award at ESEC/FSE 2022 in Singapore.

11/2022: IEEE TSE! Our paper: “DiffSearch: A Scalable and Precise Search Engine for Code Changes” has been accepted for the IEEE Transactions on Software Engineering journal.

10/2022: ACM CSUR! Our paper: “Code Search: A Survey of Techniques for Finding Code” has been accepted for the ACM Computing Surveys journal.

09/2022: ESEC/FSE! Our paper: “The Evolution of Type Annotations in Python: An Empirical Study” has been accepted for the ESEC/FSE 2022 conference.

05/2022: ICSE SRC 2022! Winner of the second prize ($300) for the ICSE ACM Student Research Competition (SRC) with the submission “Efficiently and Precisely Searching for Code Changes with DiffSearch”.

Peer-reviewed Publications

The Evolution of Type Annotations in Python:
An Empirical Study

ESEC/FSE 2022
ACM SIGSOFT Distinguished Paper Award

We extract 1.4 million type annotation changes from 9,655 Python repositories. Our results show that type annotations are clearly gaining traction, yet the large majority of code elements that could be annotated currently remains unannotated. We see a huge potential for techniques that automate the process of adding types into an existing code base, such as neural type prediction models. Finally, many developers seem to not regularly check their code for statically detectable type errors, or if they do, commit the code despite such errors.
Finally, many developers seem to not regularly check their code for statically detectable type errors, or if they do, commit the code despite such errors.

DiffSearch: A Scalable and Precise Search Engine for Code Changes

IEEE Transactions on Software Engineering (TSE), 2022
2nd prize winner at ICSE Student Research Competition 2022
and Journal-first track at ASE 2023

We present a scalable and precise search engine for code changes. Given a query, the approach retrieves within seconds relevant examples from million code changes. Our query language extends the underlying programming language, providing an intuitive way of formulating queries to search for code changes. DiffSearch guarantees that every returned search result fits the query.
We present a scalable and precise search engine for code changes.

Code Search: A Survey of Techniques for Finding Code

ACM Computing Surveys (CSUR), 2022

This article provides a comprehensive overview of 30 years of research on code search. Given the huge amounts of existing code, searching for specific code examples is a common activity during software development. We discuss what kinds of queries code search engines support, and give an overview of the main components used to retrieve suitable code examples. In particular, the article discusses techniques to pre-process and expand queries, approaches toward indexing and retrieving code, and ways of pruning and ranking search results.
the article discusses techniques to pre-process and expand queries, approaches toward indexing and retrieving code, and ways of pruning and ranking search results.

A new method for protein characterization and classification using geometrical features for 3D face analysis

Proteins: Structure, Function, and Bioinformatics, 2020

The first part of this study focused on building the protein dataset using a simulation tool and performing feature extraction using novel geometrical descriptors. The second part involved in a classification of tubulin isotypes and a comparison of tubulin with the FtsZ protein.
The second part involved in a classification of tubulin isotypes and a comparison of tubulin with the FtsZ protein.

3D Facial Expression Recognition for Defining Users Inner Requirements

Applied Sciences, 2019

This study proposes a novel quality function deployment (QFD) design methodology based on customers emotions conveyed by facial expressions. The current advances in pattern recognition related to face recognition techniques have fostered the cross-fertilization and pollination between this context and other fields, such as product design and human-computer interaction.
This study proposes a novel quality function deployment (QFD) design methodology based on customers emotions conveyed by facial expressions.

Imprint © MIT License.