activity
20172025
most citedTypilus: Neural Type Hints

88 citations · 110 across the 7 of their papers we have counts for

collaborators

15 papers

cs.SE2025

Disproving Program Equivalence with LLMs

Miltiadis Allamanis, Pengcheng Yin

To evaluate large language models (LLMs) for code, research has used manually created unit test-based benchmarks. However, these tests are often inadequate, missing corner cases an…

cs.CL20221 cited

Is Surprisal in Issue Trackers Actionable?

James Caddy, Markus Wagner, Christoph Treude +2

Background. From information theory, surprisal is a measurement of how unexpected an event is. Statistical language models provide a probabilistic approximation of natural language…

cs.LG2021

CoRGi: Content-Rich Graph Neural Networks with Attention

Jooyeon Kim, Angus Lamb, Simon Woodhead +3

Graph representations of a target domain often project it to a set of entities (nodes) and their relations (edges). However, such projections often miss important and rich informat…

cs.LG2020

Copy that! Editing Sequences by Copying Spans

Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue t…

cs.PL202088 cited

Typilus: Neural Type Hints

Miltiadis Allamanis, Earl T. Barr, Soline Ducousso +1

Type inference over partial contexts in dynamically typed languages is challenging. In this work, we present a graph neural network model that predicts types by probabilistically r…

cs.SE2020

Fast and Memory-Efficient Neural Code Completion

Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi +3

Code completion is one of the most widely used features of modern integrated development environments (IDEs). While deep learning has made significant progress in the statistical p…