Arjun Guha

About

I have broad research interests in programming languages, systems, and software engineering. For the past few years, my group has been working on language design problems that arise in WebAssembly, program synthesis for robot control programs, and developing Code LLMs for low-resource programming languages and novel tasks.

I teach a variety of undergraduate and graduate courses. I have been the lead instructor for Northeastern's CS1 course several times, designed several new courses, and taught graduate seminars on topics as varied as Code LLM development and program verification.

I also serve as the Area Chair for Software at Northeastern's Khoury College of Computer Sciences.

Fall 2024: Engineering LLM-Integrated Systems

Recent News

• Launch of the National Deep Inference Fabric (NDIF), a computing resource that enables detailed and reproducible experiments on large pretrained AI models such as LLMs (May 2024)
• Preprint: Activation Steering for Robust Type Prediction in CodeLLMs (April 2024)
• How Beginning Programmers and Code LLMs (Mis)read Each Other will appear at CHI 2024 (March 2024)
• StarCoder 2 and The Stack 2 are out (February 2024)
• Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions will appear at the LLM4Code Workshop (January 2024)
• StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code a benchmark of will appear at the LLM4Code Workshop (January 2024)
• Deploying and Evaluating LLMs to Program Service Mobile Robots will appear in IEEE Robotics and Automation Letters (January 2024)
• Preprint: Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs (August 2023)
• Received an NSF Award for research on Code LLMs for programming in the sciences, with Carolyn Jane Anderson, Molly Q Feldman, and Erin G. Teich (August 2023)
• Received a JPMorgan Chase Faculty Research Award, with Joydeep Biswas (August 2023)
• Continuing WebAssembly with Effect Handlers will appear at OOPSLA 2023 (July 2023)
• StarCoder: An Open 15B Parameter Large Language Model of Code is now available (May 2023)
• Received a MathWorks Microgrant (May 2023)
• MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation will appear in IEEE Transactions on Software Engineering (April 2023)
• A Large Scale Analysis of Semantic Versioning in NPM will appear at MSR 2023 (March 2023)
• SantaCoder will appear at the DL4C workshop (March 2023)

Research Group

I am a member of the Programming Research Laboratory at Northeastern. I work with a great group of students:

• Federico Cassano (undergrad)
• Claire Schlesinger (undergrad)
• Francesca Lucchetti (PhD)
• John Gouwar (PhD)
• James Perretta (PhD, co-advised with Jonathan Bell)
• Luna Phipps-Costin (PhD)
• Donald Pinckney (PhD)
• Yangtian Zi (PhD)

Alumni

• Abhinav Jangda (PhD → Microsoft Research)
• Ming-Ho Yee (PhD → Meta)
• Samuel Baxter (MS)
• Rian Shambaugh (MS)
• Emily Herbert (MS)
• Sam Lee (undergrad)
• Christopher Rybicki (undergrad → MS student at Cornell Tech)
• Rachit Nigam (undergrad → PhD student at Cornell)
• Nicole Andrews (Mount Holyoke College undergrad)
• Jenna Hammond (Mount Holyoke College undergrad, CRA honorable mention)
• Sydney Nguyen (Wellesley College undergrad)
• Anders Freeman (Wellesley College undergrad → PhD student at University of Massachusetts Amherst)
• Harsh Poddar (undergrad → Meta)
• Aaron Weiss (undergrad, NSF Fellow → PhD student at Northeastern University)
• Jane Tangen (undergrad → MITRE)
• Akshay Gadre (undergrad → PhD student at Carnegie Mellon)
• Nimish Gupta (MS → Amazon)

Contact