Scholar
Parth Thakkar
Google Scholar ID: lHL7TqAAAAAJ
Meta
Citations & Impact
Citations
813
H-index
6
i10-index
4
Publications
16
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- - Exploring the design space of AI based code completion engines (MS Thesis, UIUC).
- - Configuration validation with large language models (accepted at ICSE 2025).
- - Multi-line AI-assisted Code Authoring (accepted at FSE 2024).
- - Probing numeracy and logic of language models of code (accepted at InteNSE 2023).
- - Optimizing Network Provisioning through Cooperation (accepted at NSDI 2022).
- - AutoSens: Inferring Latency Sensitivity of User Activity through Natural Experiments (accepted at ACM IMC 2021).
- - Scaling Hyperledger Fabric Using Pipelined Execution and Sparse Peers (accepted at ACM SoCC 2021).
- - Performance Benchmarking and Optimization of Hyperledger Fabric (accepted at IEEE Mascots '18, Best Paper Award).
Research Experience
- - Worked with Dr. Venkat Padmanabhan at Microsoft Research, India, on optimizing WAN provisioning and measuring the impact of latency on users.
- - Worked with Dr. Senthil Nathan and Dr. Praveen Jayachandran at IBM Research, India, on improving the performance and scaling of Blockchains.
Education
- Graduated with an MS from the University of Illinois at Urbana-Champaign (UIUC) in 2023.
Background
- Research Interests: Applying Machine Learning and Program Synthesis techniques to make software development easier. Thesis: Exploring the design space of AI based code completion engines.
Miscellany
- - Personal Projects: Copilot Explorer (2022), delved into the internals of Github Copilot, wrote a tool to decompile Copilot's VSCode extension, and identified key insights regarding prompt construction logic, post-processing of model's output, and telemetry collection.
- - Core Contributor to FauxPilot (2022), an open-source alternative to Copilot, allowing it to use any HuggingFace model by supporting the Python backend model, and provided groundwork for enabling continuous integration.
- - Writings: Blog post 'Copilot Internals' (2022) and 'Doing Distributed Systems - the Bitcoin way! (Part 1)' (2017).
