Welcome to Rangeet Pan’s homepage

Rangeet Pan is a staff research scientist at the IBM T.J. Watson Research Center, Yorktown Heights. His research interests are in the field of software engineering focusing on program analysis and the use of large language models. His works at IBM Research have been focused on the use of static analysis and large language models (LLM) in various code-related tasks, e.g., code translation, test generation, etc. He has also developed a Python library named CLDK to analyze code.

For latest updates, please visit to IBM Research page.

Publications

2025

* Rangeet Pan, Myeongsoo Kim, Rahul Krishna, Raju Pavuluri, Saurabh Sinha. ASTER: Natural and Multi-language Unit Test Generation with LLMs, ICSE 2025 Industry Track [paper] (ACM Sigsoft Distinguished Paper Award)

* Rahul Krishna, Rangeet Pan, Raju Pavuluri, Maja Vukovic, Saurabh Sinha. Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights Tool Demo, ICSE 2025 Demo Track [paper]

* Ali Reza Ibrahimzada, Kaiyao Ke, Mrigank Pawagi, Muhammad Salman Abid, Rangeet Pan, Saurabh Sinha, Reyhaneh Jabbarvand. AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation, FSE 2025 [paper]

* Rahul Krishna, Rangeet Pan, Raju Pavuluri, Srikanth Tamilselvam, Maja Vukovic, Saurabh Sinha. Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights, FSE 2025 Industry Track [paper]

* Toufique Ahmed, Jatin Ganhotra, Rangeet Pan, Avraham Shinnar, Saurabh Sinha, Martin Hirzel. Otter: Generating Tests from Issues to Validate SWE Patches, ICML 2025 [paper]

2024
* Rangeet Pan, Ali Reza Ibrahimzada, Rahul Krishna, Divya Sankar, Lambert Pouguem Wassi, Michele Merler, Boris Sobolev, Raju Pavuluri, Saurabh Sinha, Reyhaneh Jabbarvand. Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code, ICSE 2024 [paper]

2023
* Rangeet Pan, Rahul Krishna, Divya Sankar, Saurabh Sinha, Julian Dolby, and Raju Pavuluri. Towards Supporting Universal Static Analysis using WALA, PLDI Tutorial, 2023

* Sayem Imtiaz, Fraol Batole, Astha Singh, Rangeet Pan, Breno Dantas Cruz and Hridesh Rajan. Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement, ICSE, 2023

2022
* Rangeet Pan and Hridesh Rajan. Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules, ICSE, 2022

* Giang Nguyen, Md.Johirul Islam, Rangeet Pan, and Hridesh Rajan. Manas: Mining Software Repositories to Assist AutoML, ICSE, 2022

2021
* Rangeet Pan, Vu Le, Nachiappan Nagappan, Sumit Gulwani, Shuvendhu Lahiri, Mike Kaufman. Can Program Synthesis be Used to Learn Merge Conflict Resolutions? An Empirical Analysis, ICSE, 2021: [pre-print] [presentation video] [blog]

2020
* Rangeet Pan, Hridesh Rajan. On Decomposing a Deep Neural Network into Modules, ESEC/FSE, 2020: 889-900 [paper]

* Rangeet Pan. Does Fixing Bug Increase Robustness in Deep Learning?, ICSE SRC, 2020: 146-148 [paper]

* Md Johirul Islam, Rangeet Pan, Hridesh Rajan. Repairing Deep Neural Networks: Fix Patterns and Challenges, ICSE, 2020: 1135-1146 [paper]

2019
* Md Johirul Islam, Giang Nguyen, Rangeet Pan, Hridesh Rajan. A Comprehensive Study on Deep Learning Bug Characteristics, ESEC/FSE, 2019 : 510-520 [paper]

* Rangeet Pan. Static Deep Neural Network Analysis for Robustness, ESEC/FSE SRC, 2019: 1238-1240 [paper]

Interns

1. Tyle Stennett (summer 2025), Georgia Tech
2. Shuyang Liu (summer 2025), UIUC
3. Myeongsoo Kim (summer 2024), Georgia Tech, currently at Amazon Science
4. Ali Reza Ibrahimreza (summer 2023 and 2024), UIUC

Recent News!

* June ‘22: Joined IBM Research as a research staff member.

* June ‘22: Defended my dissertation on decomposing deep learning models into modules.

* May ‘22: Attended and presented our works at ICSE’22.

* Aug ‘21: Our work on resolving merge conflict has been featured at Microsoft Research blog.

* July ‘21: Invited to present our ICSE’21 paper on merge conflict at UC Davis Computer Science seminar.

* June ‘21: Serving as a PC member of OOPSLA Artifact.

* May ‘21: Presented our paper on “Can Program Synthesis be Used to Learn Merge Conflict Resolutions? An Empirical Analysis” at ICSE 2021.

* May ‘21: Awarded “Research Excellence Award” by Department of Computer Science, Iowa State University for the works done during the Ph.D. program.

* May ‘21: Passed Ph.D. preliminary examination.

* Apr ‘21: Presented my research talk on “Characterizing Deep Neural Networks and Merge Conflicts” at Microsoft PROSE.

* Jan ‘21: Awarded SIGSOFT CAPS Funding Award for ICSE 2021 registration.

* Jan ‘21: Our paper on “Can Program Synthesis be Used to Learn Merge Conflict Resolutions? An Empirical Analysis” has been accepted at ICSE 2021.

* Jan ‘21: I will be serving as Shadow PC member at MSR 2021.

* Nov ‘20: ACM SIGSOFT Distinguished paper award at ESEC/FSE for “On Decomposing Deep Neural Networks into Modules”.

* Nov ‘20: Present our paper “On Decomposing Deep Neural Networks into Modules” at ESEC/FSE, 2020.

* May ‘20: Join Microsoft Research as a research intern.

* May ‘20: Won 2nd place at the ACM Student Research Competition, ICSE, 2020.

* May ‘20: Present SRC paper “Does Fixing Bug Increase Robustness in Deep Learning?”, ICSE, 2020.

* Dec ‘19: Our paper on “On Decomposing Deep Neural Networks into Modules” has been accepted at ESEC/FSE, 2020

* May ‘20: Won Robert Stewart Early Research Recognition Award, Iowa State University, 2020.

* Dec ‘19: Our paper on “Repairing Deep Neural Networks: Fix Patterns and Challenges” has been accepted at ICSE, 2020

* Aug ‘19: Present our paper on “A Comprehensive Study on Deep Learning Bug Characteristics” at ESEC/FSE, 2019, Estonia, Tallinn

* May ‘19: Our paper on “A Comprehensive Study on Deep Learning Bug Characteristics” has been accepted at ESEC/FSE, 2019

* Aug ‘18: Join Ph.D. program at the Department of Computer Science at Iowa State University

Personal

I am originally from Chandannagar, which is one of the two French colonies in India. I love to play with Lego and console games. Recently completed Witcher 3: Wild Hunt and now playing Horizon Zero Dawn.