Search Results - "Allamanis, Miltiadis"

Embedding and classifying test execution traces using neural networks by Tsimpourlas, Foivos, Rooijackers, Gwenyth, Rajan, Ajitha, Allamanis, Miltiadis

“…Classifying test executions automatically as pass or fail remains a key challenge in software testing and is referred to as the test oracle problem. It is…”
Get full text

Why, when, and what: Analyzing Stack Overflow questions by topic, type, and code by Allamanis, Miltiadis, Sutton, Charles

“…Questions from Stack Overflow provide a unique opportunity to gain insight into what programming concepts are the most confusing. We present a topic modeling…”
Get full text

CODIT: Code Editing With Tree-Based Neural Models by Chakraborty, Saikat, Ding, Yangruibo, Allamanis, Miltiadis, Ray, Baishakhi

“…The way developers edit day-to-day code tends to be repetitive, often using existing code elements. Many researchers have tried to automate repetitive code…”
Get full text

JEMMA: An extensible Java dataset for ML4Code applications by Karmakar, Anjan, Allamanis, Miltiadis, Robbes, Romain

“…Machine Learning for Source Code (ML4Code) is an active research field in which extensive experimentation is needed to discover how to best use source code’s…”
Get full text

Autofolding for Source Code Summarization by Fowkes, Jaroslav, Chanthirasegaran, Pankajan, Ranca, Razvan, Allamanis, Miltiadis, Lapata, Mirella, Sutton, Charles

“…Developers spend much of their time reading and browsing source code, raising new opportunities for summarization methods. Indeed, modern code editors provide…”
Get full text

Mining source code repositories at massive scale using language modeling by Allamanis, Miltiadis, Sutton, Charles

“…The tens of thousands of high-quality open source software projects on the Internet raise the exciting possibility of studying software development by finding…”
Get full text

Mining Semantic Loop Idioms by Allamanis, Miltiadis, Barr, Earl T., Bird, Christian, Devanbu, Premkumar, Marron, Mark, Sutton, Charles

“…To write code, developers stitch together patterns, like API protocols or data structure traversals. Discovering these patterns can identify inconsistencies in…”
Get full text

DIRE: A Neural Approach to Decompiled Identifier Naming by Lacomis, Jeremy, Yin, Pengcheng, Schwartz, Edward, Allamanis, Miltiadis, Le Goues, Claire, Neubig, Graham, Vasilescu, Bogdan

“…The decompiler is one of the most common tools for examining binaries without corresponding source code. It transforms binaries into high-level code, reversing…”
Get full text

Learning natural coding conventions by Allamanis, Miltiadis

“…Coding conventions are ubiquitous in software engineering practice. Maintaining a uniform coding style allows software development teams to communicate through…”
Get full text

Epicure: Distilling Sequence Model Predictions into Patterns by Allamanis, Miltiadis, Barr, Earl T

“…Most machine learning models predict a probability distribution over concrete outputs and struggle to accurately predict names over high entropy sequence…”
Get full text

The Adverse Effects of Code Duplication in Machine Learning Models of Code by Allamanis, Miltiadis

“…The field of big code relies on mining large corpora of code to perform some learning task. A significant threat to this approach has been recently identified…”
Get full text

Fast and Memory-Efficient Neural Code Completion by Svyatkovskiy, Alexey, Lee, Sebastian, Hadjitofi, Anna, Riechert, Maik, Franco, Juliana Vicente, Allamanis, Miltiadis

“…Code completion is one of the most widely used features of modern integrated development environments (IDEs). While deep learning has made significant progress…”
Get full text

Unsupervised Evaluation of Code LLMs with Round-Trip Correctness by Allamanis, Miltiadis, Panthaplackel, Sheena, Yin, Pengcheng

“…To evaluate code large language models (LLMs), research has relied on a few small manually curated benchmarks, such as HumanEval and MBPP, which represent a…”
Get full text

JEMMA: An Extensible Java Dataset for ML4Code Applications by Karmakar, Anjan, Allamanis, Miltiadis, Robbes, Romain

“…Machine Learning for Source Code (ML4Code) is an active research field in which extensive experimentation is needed to discover how to best use source code's…”
Get full text

Keynote abstract by Allamanis, Miltiadis

“…Provides an abstract of the keynote presentation and a brief professional biography of the presenter. The complete presentation was not made available for…”
Get full text

HEAT: Hyperedge Attention Networks by Georgiev, Dobrik, Brockschmidt, Marc, Allamanis, Miltiadis

“…Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary…”
Get full text

Self-Supervised Bug Detection and Repair by Allamanis, Miltiadis, Jackson-Flux, Henry, Brockschmidt, Marc

“…Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development…”
Get full text

NExT: Teaching Large Language Models to Reason about Code Execution by Ni, Ansong, Allamanis, Miltiadis, Cohan, Arman, Deng, Yinlin, Shi, Kensen, Sutton, Charles, Yin, Pengcheng

“…A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate…”
Get full text

Do Large Code Models Understand Programming Concepts? A Black-box Approach by Hooda, Ashish, Christodorescu, Mihai, Allamanis, Miltiadis, Wilson, Aaron, Fawaz, Kassem, Jha, Somesh

“…Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their…”
Get full text

AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations by Liu, Xiaoyu, Jang, Jinu, Sundaresan, Neel, Allamanis, Miltiadis, Svyatkovskiy, Alexey

“…In software development, it is common for programmers to copy-paste or port code snippets and then adapt them to their use case. This scenario motivates the…”
Get full text