Toufique Ahmed

My present research focuses on enhancing Large Language Models (LLMs) to achieve excellence in Software Engineering. This entails a dual emphasis on elevating performance and ensuring trustworthiness. Broadly speaking, my work resides at the intersection of machine learning and software engineering to harness the power of machine learning to alleviate the burdens faced by software developers, ultimately fostering increased productivity. I am privileged to receive guidance from Prof. Prem Devanbu and my works have been published in the most prestigious Software Engineering venues including ICSE, ESEC/FSE, ASE, TSE, and EMSE.

Email: TFAHMED @ UNIVERSITY of CALIFORNIA DAVIS . EDUCATION
#bold-italic characters #lower case #without space

Links:   Google Scholar    Twitter    LinkedIn

Your Photo

News

  1. Dec 15, 2023: Our Paper "Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)" has been accepted at ICSE, 2024

  2. Nov 15, 2023: I am serving as Web Co-chair at ASE, 2024

  3. Jul 7, 2023: Our Paper "Better patching using LLM prompting, via Self-Consistency" has been accepted at ASE-NIER, 2023

  4. Mar 7, 2023: Our Paper "Large Language Models and Simple, Stupid Bugs" has been accepted at MSR, 2023

  5. Dec 8, 2022: Our Paper "Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models" has been accepted at ICSE, 2023

Education

PhD in Computer Science, September 2018 - June 2023
University of California Davis
California, USA
Advisor: Prof. Prem Devanbu
Thesis: Learning Program Embedding form Unlabeled Source Code

MSc in Computer Science and Engineering, 2014 - 2016
Bangladesh University of Engineering and Technology (BUET)
Dhaka, Bangladesh

BSc in Computer Science and Engineering, 2009 - 2014
Bangladesh University of Engineering and Technology (BUET)
Dhaka, Bangladesh

Experience

University of California, Davis
California, USA
Postdoctoral Scholar, 2023 -present
Dean's Disguised Graduate Fellow, 2018 - 2023

Microsoft Research, Redmond
Washington, USA
Research Intern, June, 2022 - September, 2022

Bangladesh University of Engineering and Technology (BUET)
Dhaka, Bangladesh
Teaching Faculty, 2014 - 2018

Selected Publications

In Reverse Chronological Order:

  1. Toufique Ahmed, Kunal Pai, Premkumar Devanbu and Earl T. Barr. "Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)", accepted at International Conference on Software Engineering (ICSE-2024). Link

  2. Toufique Ahmed and Premkumar Devanbu. "Better patching using LLM prompting, via Self-Consistency", accepted at IEEE/ACM International Conference on Automated Software Engineering - The New Ideas and Emerging Results track (ASE-NIER-2023). Link

  3. Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang and Saravan Rajmohan. "Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models", accepted at International Conference on Software Engineering (ICSE-2023). Link

  4. Kevin Jesse, Toufique Ahmed, Premkumar T Devanbu, and Emily Morgan. "Large Language Models and Simple, Stupid Bugs", Accepted at International Conference on Mining Software Repositories (MSR-2023). Link

  5. Ali Al-Kaswan, Toufique Ahmed, Maliheh Izadi, Anand Ashok Sawant, Prem Devanbu, Arie van Deursen. "Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries", Accepted at IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER-2023). Link

  6. Toufique Ahmed, Noah Rose Ledesma, and Premkumar Devanbu. "SYNSHINE: improved fixing of Syntax Errors", Accepted at IEEE Transactions on Software Engineering (TSE-2022). Link

  7. Toufique Ahmed and Premkumar Devanbu. "Few-shot training LLMs for project-specific code-summarization", accepted at IEEE/ACM International Conference on Automated Software Engineering - The New Ideas and Emerging Results track (ASE-NIER-2022). Link

  8. Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu, and Baishakhi Ray. "NatGen: Generative pre-training by Naturalizing source code", accepted at European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE-2022). Link

  9. Toufique Ahmed and Premkumar Devanbu. "Multilingual training for Software Engineering", accepted at International Conference on Software Engineering (ICSE-2022). Link

  10. Toufique Ahmed, Premkumar Devanbu, and Anand Ashok Sawant. "Learning to Find Usages of Library Functions in Optimized Binaries", accepted at IEEE Transactions on Software Engineering (TSE-2021). Link

  11. Kevin Jesse, Premkumar Devanbu, and Toufique Ahmed. "Learning type annotation: is big data enough?", accepted at Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE-IVR-2021). Link

  12. Toufique Ahmed, Premkumar Devanbu, and Vincent J Hellendoorn. "Learning Lenient Parsing & Typing via Indirect Supervision", accepted at Empirical Software Engineering Journal (EMSE-2021). Link

  13. Toufique Ahmed, Amiangshu Bosu, Anindya Iqbal, and Shahram Rahimi. "SentiCR: A Customized Sentiment Analysis Tool for Code Review Interactions.", accepted at IEEE/ACM International Conference on Automated Software Engineering - The New Ideas and Emerging Results track (ASE-NIER-2017). Link

Awards and Recognitions

Selected Talks

Services

Reviewer

Student Mentored

Teaching

Bangladesh University of Engineering and Technology (BUET)