Vincent Hellendoorn
Vincent Hellendoorn
Verified email at - Homepage
Cited by
Cited by
Are deep neural networks the best choice for modeling source code?
VJ Hellendoorn, P Devanbu
Proceedings of the 2017 11th Joint meeting on foundations of software …, 2017
A systematic evaluation of large language models of code
FF Xu, U Alon, G Neubig, VJ Hellendoorn
Proceedings of the 6th ACM SIGPLAN International Symposium on Machine …, 2022
On the "naturalness" of buggy code
B Ray, V Hellendoorn, S Godhane, Z Tu, A Bacchelli, P Devanbu
Software Engineering (ICSE), 2016 IEEE/ACM 38th International Conference on …, 2016
Global Relational Models of Source Code
VJ Hellendoorn, Maniatis, P, R Singh, C Sutton, D Bieber
International Conference on Learning Representations, 2020
Deep learning type inference
VJ Hellendoorn, C Bird, ET Barr, M Allamanis
Proceedings of the 2018 26th acm joint meeting on european software …, 2018
Will they like this? Evaluating code contributions with language models
VJ Hellendoorn, PT Devanbu, A Bacchelli
2015 IEEE/ACM 12th Working Conference on Mining Software Repositories, 157-167, 2015
When code completion fails: A case study on real-world completions
VJ Hellendoorn, S Proksch, HC Gall, A Bacchelli
2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE …, 2019
Cacheca: A cache language model based code suggestion tool
C Franks, Z Tu, P Devanbu, V Hellendoorn
2015 IEEE/ACM 37th IEEE International Conference on Software Engineering 2 …, 2015
Understanding Neural Code Intelligence Through Program Simplification
M Rafiqul Islam Rabin, VJ Hellendoorn, MA Alipour
arXiv e-prints, arXiv: 2106.03353, 2021
Patching as translation: the data and the metaphor
Y Ding, B Ray, P Devanbu, VJ Hellendoorn
Proceedings of the 35th IEEE/ACM International Conference on Automated …, 2020
Diffuser: Diffusion via edit-based reconstruction
M Reid, VJ Hellendoorn, G Neubig
The Eleventh International Conference on Learning Representations, 2022
Perceived language complexity in GitHub issue discussions and their effect on issue resolution
D Kavaler, S Sirovica, V Hellendoorn, R Aranovich, V Filkov
2017 32nd IEEE/ACM International Conference on Automated Software …, 2017
PLUR: A unifying, graph-based view of program learning, understanding, and repair
Z Chen, VJ Hellendoorn, P Lamblin, P Maniatis, PA Manzagol, D Tarlow, ...
Advances in Neural Information Processing Systems 34, 23089-23101, 2021
Memorization and Generalization in Neural Code Intelligence Models
M Rafiqul Islam Rabin, A Hussain, MA Alipour, VJ Hellendoorn
arXiv e-prints, arXiv: 2106.08704, 2021
Patch generation with language models: Feasibility and scaling behavior
SD Kolak, R Martins, C Le Goues, VJ Hellendoorn
Deep Learning for Code Workshop, 2022
Revisiting test smells in automatically generated tests: limitations, pitfalls, and opportunities
A Panichella, S Panichella, G Fraser, AA Sawant, VJ Hellendoorn
2020 IEEE international conference on software maintenance and evolution …, 2020
Learning Lenient Parsing & Typing via Indirect Supervision
T Ahmed, P Devanbu, VJ Hellendoorn
Empirical Software Engineering 26 (2), 1-31, 2021
Towards Automating Code Review at Scale
VJ Hellendoorn, J Tsay, M Mukherjee, M Hirzel
Proceedings of the 29th ACM Joint Meeting on European Software Engineering …, 2021
The Growing Cost of Deep Learning for Source Code
VJ Hellendoorn, AA Sawant
Communications of the ACM 65 (1), 31-33, 2022
Test smells 20 years later: detectability, validity, and reliability
A Panichella, S Panichella, G Fraser, AA Sawant, VJ Hellendoorn
Empirical Software Engineering 27 (7), 170, 2022
The system can't perform the operation now. Try again later.
Articles 1–20