Miltiadis Allamanis

Registered user since Fri 15 Sep 2017

Name: Miltiadis Allamanis

Country: United Kingdom

Affiliation: Microsoft Research, UK

Personal website:



Research interests: Machine Learning, Deep Learning


MSR 2021 Mining Challenge Co-Chair in Organizing Committee
Mining Challenge Co-Chair in Mining Challenge Committee within the Mining Challenge-track
Session Chair of Mining Challenge Session (part of Technical Papers)
Author of Fast and Memory-Efficient Neural Code Completion within the Technical Papers-track
ESEC/FSE 2021 Industry Co-Chair in Organizing Committee
Co-chair in Program Committee within the Industry Papers-track
ESEC/FSE 2020 Author of Flexeme: Untangling Commits Using Lexical Flows within the Research Papers-track
Committee Member in Program Committee within the Visions and Reflections -track
MSR 2020 Ordinary PC member in Program Committee within the Technical Papers-track
Committee Member in Program Committee within the Data Showcase-track
Panelist of ML4SE AMA within the Ask Me Anything-track
PLDI 2020 Author of Typilus: Neural Type Hints within the PLDI Research Papers-track
ICSE 2021 Author of CODIT: Code Editing with Tree-Based Neural Models within the Journal-First Papers-track
ASE 2019 Author of DIRE: A Neural Approach to Decompiled Identifier Renaming within the Research Papers-track
SPLASH 2019 Author of The Adverse Effects of Code Duplication in Machine Learning Models of Code within the Onward! Papers-track
Invited Speaker of Machine Learning for Program Analysis within the Rebase-track
VMCAI 2019 Committee Member in Program Committee within the VMCAI 2019-track
ML4PL 2018 Committee Member in Program Committee within the ML4PL-track
ESEC/FSE 2018 Author of Mining Semantic Loop Idioms within the Journal-First-track
Author of RefiNym: Using Names to Refine Types within the Research Papers-track
Author of Deep Learning Type Inference within the Research Papers-track
PLDI 2018 Committee Member in External Review Committee
ML4PL 2015 Author of Inferring Coding Conventions with Machine Learning within the ML4PL-track