DiffSpec: Differential Testing with LLMs using Natural Language Specifications and Code Artifacts - Under Submission, 2024 [arXiv] [code]
CURRICULUM VITAE
The detailed PDF verison of my CV can be found here - CV
Research Interests
I seek to build systems using data-driven techniques.
- Domains - Data Science, Machine Learning, Data Analysis and Machine Learning for Software Engineering, Information Retrival, Data Mining, Web Search Log Analysis
Publications
- Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts - Under Submission, 2024 [arXiv]
- CAT-LM: Training Language Models on Aligned Code And Tests - Automated Software Engineering (ASE), 2023 [paper] [arXiv] [code]
- Comments on Comments: Where Code Review and Documentation Meet - Mining Software Repositories (MSR), 2022 [paper] [arXiv]
- Search4Code: Code Search Intent Classification Using Weak Supervision - Mining Software Repositories (MSR), 2021 [paper] [arXiv]
- Neural Knowledge Extraction From Cloud Service Incidents - 43rd International Conference on Software Engineering (ICSE SEIP), 2021 [paper] [arXiv]
- Analyzing Web Search Behavior for Software Engineering Tasks - IEEE International Conference on Big Data (IEEE BigData), 2020 [paper] [arXiv]
- Product Insights: Analyzing Product Intents in Web Search - 29th ACM International Conference on Information and Knowledge Management (CIKM), 2020 [paper] [arXiv]
- Studying Ransomware Attacks Using Web Search Logs - 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020 [paper] [arXiv]
- Analysis of Joints for Tracking Fitness and Monitoring Progress in Physiotherapy - IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2019 [paper]
Preprints
Patents
- ‘Identification of Content Gaps based on Relative User-Selection Rates between Multiple Discrete Content Sources’ filed with the USPTO (October 16, 2020).
- Co-inventors: Chetan Bansal, Junia George, Casey Gossard, Dung Nguyen, Dave Ludwig, Curtis Anderson.
- ‘ExtraQuery Context-Aided Search Intent Detection’ filed with the USPTO (October 9, 2020).
- Co-inventors: Chetan Bansal, Joe Guan, Mark Wilson-Thomas, Nachiappan Nagappan, Thomas Zimmermann.
- ‘Automatic Recognition of Entities Related to Cloud Incidents’ filed with the USPTO (June 19, 2020).
- Co-inventors: Manish Shetty, Chetan Bansal, Sumit Kumar, Nachiappan Nagappan, Thomas Zimmermann.
Education
- Bachelor’s in Technology (B.Tech) from PES University (previously known as PES Institute of Technology or PESIT)
- Major - Computer Science and Engineering
- Specialization - Data Science
Work Experience
- July 2019 - Present: Research Fellow
- Microsoft Research Lab - India
- Mentor - Chetan Bansal
- Project Domains - Search Insights, AI for DevOps (Project Sankie)
- January 2019 - June 2019: Research Intern
- Microsoft Research Lab - India
- Advisor - Dr. Sreangsu Acharyya
- Problem Statement - Designed an algorithm to learn rankings under extreme class imbalance by maximizing the partial area under ROC curve.
- Summer 2018: Research Intern
- Carnegie Mellon University, Pittsburgh
- Advisor - Dr. Shawn Blanton
- Problem Statement - Analysis of various patterns in the input-output sequences of various obfuscated circuits to define a metric to quantify the level of obfuscation in a circuit using machine learning techniques.
- Summer School Program 2017
- Was among the youngest students selected for the 5th Summer School Program conducted by the Computer Science and Automation (CSA) Department at the Indian Institute of Science, India. (July ‘17)
- Summer 2017: Summer Research Intern
- Microsoft Innovation Lab
- Worked in the domain of Virtual Reality and Machine Learning.
- Problem Statement - Designed a system to track progress in children having cerebral palsy by gamifying the physiotherapy process.
- Core member in organizing a course on analysis and thinking - 2017 that was a week-long program in which I delivered a workshop on logical thinking. (July ‘17)
Projects
- Search4Code: Code Search Intent Classification Using Weak Supervision - Microsoft Research Lab - India
- Handling Class Imbalance with POISE: pAUC Optimization in Supervised Experiments - Microsoft Research Lab - India
- Neural Knowledge Extraction From Cloud Service Incidents - Microsoft Research Lab - India
- Analyzing Web Search Behavior for Software Engineering Tasks - Microsoft Research Lab - India
- Studying Ransomware Attacks Using Web Search Logs - Microsoft Research Lab - India
- Product Insights: Analyzing Product Intents in Web Search - Microsoft Research Lab - India
- Analysis of Joints for Tracking Fitness and Monitoring Progress in Physiotherapy - PES Center for Pattern Recognition, PES University
- Retinopathy of Prematurity – Feature Engineering and Predictive Analysis - PES University in collaboration with Rx Digi Health Platform
- Analysis of Adversarial Attacks To Fool Deep Networks - PES University
- Defining the Level of Hardware Obfuscation using Machine Learning Techniques - Carnegie Mellon University
- Intent Based Duplicate Question Removal - PES University
Achievements
Won the Best Student Award in the Computer Science Department for the graduating class of 2019 at PES University.
Five time recipient of the CNR Rao scholarship for demonstrating academic excellence in Computer Science Department, PES University, India.
Winner at Datathon a data analytics based-hackathon at PES University, India. (2018)
Runner up at the TechQuiz in the Summer School Program at Computer Science and Automation department, Indian Institute of Science, Bangalore, India. (July 2017)