activity
20182022
most citedRepairing Bugs in Python Assignments Using Large Language Models

30 citations · 32 across the 4 of their papers we have counts for

collaborators

7 papers

cs.SE202230 cited

Repairing Bugs in Python Assignments Using Large Language Models

Jialu Zhang, José Cambronero, Sumit Gulwani +4

Students often make mistakes on their introductory programming assignments as part of their learning process. Unfortunately, providing custom repairs for these mistakes can require…

cs.LG20222 cited

LoopStack: a Lightweight Tensor Algebra Compiler Stack

Bram Wasti, José Pablo Cambronero, Benoit Steiner +2

We present LoopStack, a domain specific compiler stack for tensor operations, composed of a frontend, LoopTool, and an efficient optimizing code generator, LoopNest. This stack ena…

cs.SE2021

Searching for Replacement Classes

Malavika Samak, Jose Pablo Cambronero, Martin C. Rinard

Software developers must often replace existing components in their systems to adapt to evolving environments or tooling. While traditional code search systems are effective at ret…

cs.PL2021

Inferring Drop-in Binary Parsers from Program Executions

Thurston H. Y. Dang, Jose P. Cambronero, Martin C. Rinard

We present BIEBER (Byte-IdEntical Binary parsER), the first system to model and regenerate a full working parser from instrumented program executions. To achieve this, BIEBER explo…

cs.SE2019

Characterizing Developer Use of Automatically Generated Patches

José Pablo Cambronero, Jiasi Shen, Jürgen Cito +2

We present a study that characterizes the way developers use automatically generated patches when fixing software defects. Our study tasked two groups of developers with repairing…

cs.SE2019

When Deep Learning Met Code Search

Jose Cambronero, Hongyu Li, Seohyun Kim +2

There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of co…