Vincent J. Hellendoorn

52 papers A* 12A 6Journal 27Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision. CoRR Manisha Mukherjee, Vincent J. Hellendoorn
2026	J	`jnl`	The price of precision: the cost of preprocessing for automated code revision in code review. Empir. Softw. Eng. Shirin Pirouzkhah, Pooja Rani, Francesco Sovrano, Vincent J. Hellendoorn, Alberto Bacchelli
2025	A*	`conf`	An Exploratory Study of ML Sketches and Visual Code Assistants. ICSE Luís F. Gomes, Vincent J. Hellendoorn, Jonathan Aldrich, Rui Abreu
2025	J	`jnl`	Prompting LLMs for Code Editing: Struggles and Remedies. CoRR Daye Nam, Ahmed Omran, Ambar Murillo, Saksham Thakur, Abner Araujo, Marcel Blistein, Alexander Frömmgen, Vincent J. Hellendoorn, Satish Chandra
2025	A*	`conf`	Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models. ICSE Aidan Z. H. Yang, Sophia Kolak, Vincent J. Hellendoorn, Ruben Martins, Claire Le Goues
2025	J	`jnl`	SOSecure: Safer Code Generation with RAG and StackOverflow Discussions. CoRR Manisha Mukherjee, Vincent J. Hellendoorn
2025	—	`conf`	Skill over Scale: The Case for Medium, Domain-Specific Models for SE. Forge@ICSE Manisha Mukherjee, Vincent J. Hellendoorn
2024	A	`conf`	AI for Low-Code for AI. IUI Nikitha Rao, Jason Tsay, Kiran Kate, Vincent J. Hellendoorn, Martin Hirzel
2024	J	`jnl`	An Exploratory Study of ML Sketches and Visual Code Assistants. CoRR Luís F. Gomes, Vincent J. Hellendoorn, Jonathan Aldrich, Rui Abreu
2024	A*	`conf`	Large Language Models for Test-Free Fault Localization. ICSE Aidan Z. H. Yang, Claire Le Goues, Ruben Martins, Vincent J. Hellendoorn
2024	A	`conf`	Learning Defect Prediction from Unrealistic Data. SANER Kamel Alrashedy, Vincent J. Hellendoorn, Alessandro Orso
2024	J	`jnl`	Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models. CoRR Aidan Z. H. Yang, Sophia Kolak, Vincent J. Hellendoorn, Ruben Martins, Claire Le Goues
2024	A*	`conf`	Using an LLM to Help With Code Understanding. ICSE Daye Nam, Andrew Macvean, Vincent J. Hellendoorn, Bogdan Vasilescu, Brad A. Myers
2023	J	`jnl`	AI for Low-Code for AI. CoRR Nikitha Rao, Jason Tsay, Kiran Kate, Vincent J. Hellendoorn, Martin Hirzel
2023	A*	`conf`	CAT-LM Training Language Models on Aligned Code And Tests. ASE Nikitha Rao, Kush Jain, Uri Alon, Claire Le Goues, Vincent J. Hellendoorn
2023	J	`jnl`	CAT-LM: Training Language Models on Aligned Code And Tests. CoRR Nikitha Rao, Kush Jain, Uri Alon, Claire Le Goues, Vincent J. Hellendoorn
2023	A*	`conf`	Improving API Knowledge Discovery with ML: A Case Study of Comparable API Methods. ICSE Daye Nam, Brad A. Myers, Bogdan Vasilescu, Vincent J. Hellendoorn
2023	J	`jnl`	In-IDE Generation-based Information Support with a Large Language Model. CoRR Daye Nam, Andrew Macvean, Vincent J. Hellendoorn, Bogdan Vasilescu, Brad A. Myers
2023	J	`jnl`	Large Language Models for Test-Free Fault Localization. CoRR Aidan Z. H. Yang, Ruben Martins, Claire Le Goues, Vincent J. Hellendoorn
2023	J	`jnl`	Learning Defect Prediction from Unrealistic Data. CoRR Kamel Alrashedy, Vincent J. Hellendoorn, Alessandro Orso
2023	J	`jnl`	Memorization and generalization in neural code intelligence models. Inf. Softw. Technol. Md. Rafiqul Islam Rabin, Aftab Hussain, Mohammad Amin Alipour, Vincent J. Hellendoorn
2023	J	`jnl`	Stack Over-Flowing with Results: The Case for Domain-Specific Pre-Training Over One-Size-Fits-All Models. CoRR Manisha Mukherjee, Vincent J. Hellendoorn
2022	J	`jnl`	A Library for Representing Python Programs as Graphs for Machine Learning. CoRR David Bieber, Kensen Shi, Petros Maniatis, Charles Sutton, Vincent J. Hellendoorn, Daniel D. Johnson, Daniel Tarlow
2022	J	`jnl`	A Systematic Evaluation of Large Language Models of Code. CoRR Frank F. Xu, Uri Alon, Graham Neubig, Vincent J. Hellendoorn
2022	A	`conf`	Comments on Comments: Where Code Review and Documentation Meet. MSR Nikitha Rao, Jason Tsay, Martin Hirzel, Vincent J. Hellendoorn
2022	J	`jnl`	Comments on Comments: Where Code Review and Documentation Meet. CoRR Nikitha Rao, Jason Tsay, Martin Hirzel, Vincent J. Hellendoorn
2022	J	`jnl`	DiffusER: Discrete Diffusion via Edit-based Reconstruction. CoRR Machel Reid, Vincent J. Hellendoorn, Graham Neubig
2022	A	`conf`	On the Naturalness of Fuzzer-Generated Code. MSR Rajeswari Hita Kambhamettu, John Billos, Tomi Oluwaseun-Apo, Benjamin Gafford, Rohan Padhye, Vincent J. Hellendoorn
2022	J	`jnl`	Test smells 20 years later: detectability, validity, and reliability. Empir. Softw. Eng. Annibale Panichella, Sebastiano Panichella, Gordon Fraser, Anand Ashok Sawant, Vincent J. Hellendoorn
2022	J	`jnl`	The growing cost of deep learning for source code. Commun. ACM Vincent J. Hellendoorn, Anand Ashok Sawant
2021	J	`jnl`	Capturing Structural Locality in Non-parametric Language Models. CoRR Frank F. Xu, Junxian He, Graham Neubig, Vincent J. Hellendoorn
2021	J	`jnl`	Learning lenient parsing & typing via indirect supervision. Empir. Softw. Eng. Toufique Ahmed, Premkumar T. Devanbu, Vincent J. Hellendoorn
2021	J	`jnl`	Memorization and Generalization in Neural Code Intelligence Models. CoRR Md. Rafiqul Islam Rabin, Aftab Hussain, Vincent J. Hellendoorn, Mohammad Amin Alipour
2021	A*	`conf`	PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair. NeurIPS Zimin Chen, Vincent J. Hellendoorn, Pascal Lamblin, Petros Maniatis, Pierre-Antoine Manzagol, Daniel Tarlow, Subhodeep Moitra
2021	—	`conf`	Towards automating code review at scale. ESEC/SIGSOFT FSE Vincent J. Hellendoorn, Jason Tsay, Manisha Mukherjee, Martin Hirzel
2021	J	`jnl`	Understanding Neural Code Intelligence Through Program Simplification. CoRR Md. Rafiqul Islam Rabin, Vincent J. Hellendoorn, Mohammad Amin Alipour
2021	—	`conf`	Understanding neural code intelligence through program simplification. ESEC/SIGSOFT FSE Md. Rafiqul Islam Rabin, Vincent J. Hellendoorn, Mohammad Amin Alipour
2020	A*	`conf`	Global Relational Models of Source Code. ICLR Vincent J. Hellendoorn, Charles Sutton, Rishabh Singh, Petros Maniatis, David Bieber
2020	A*	`conf`	Patching as Translation: the Data and the Metaphor. ASE Yangruibo Ding, Baishakhi Ray, Premkumar T. Devanbu, Vincent J. Hellendoorn
2020	J	`jnl`	Patching as Translation: the Data and the Metaphor. CoRR Yangruibo Ding, Baishakhi Ray, Premkumar T. Devanbu, Vincent J. Hellendoorn
2020	A	`conf`	Revisiting Test Smells in Automatically Generated Tests: Limitations, Pitfalls, and Opportunities. ICSME Annibale Panichella, Sebastiano Panichella, Gordon Fraser, Anand Ashok Sawant, Vincent J. Hellendoorn
2019	J	`jnl`	Are My Invariants Valid? A Learning Approach. CoRR Vincent J. Hellendoorn, Premkumar T. Devanbu, Oleksandr Polozov, Mark Marron
2019	J	`jnl`	Learning Lenient Parsing & Typing via Indirect Supervision. CoRR Toufique Ahmed, Vincent J. Hellendoorn, Premkumar T. Devanbu
2019	A*	`conf`	When code completion fails: a case study on real-world completions. ICSE Vincent J. Hellendoorn, Sebastian Proksch, Harald C. Gall, Alberto Bacchelli
2018	—	`conf`	Deep learning type inference. ESEC/SIGSOFT FSE Vincent J. Hellendoorn, Christian Bird, Earl T. Barr, Miltiadis Allamanis
2018	—	`conf`	On the naturalness of proofs. ESEC/SIGSOFT FSE Vincent J. Hellendoorn, Premkumar T. Devanbu, Mohammad Amin Alipour
2017	—	`conf`	Are deep neural networks the best choice for modeling source code? ESEC/SIGSOFT FSE Vincent J. Hellendoorn, Premkumar T. Devanbu
2017	A*	`conf`	Perceived language complexity in GitHub issue discussions and their effect on issue resolution. ASE David Kavaler, Sasha Sirovica, Vincent J. Hellendoorn, Raúl Aranovich, Vladimir Filkov
2016	A*	`conf`	On the "naturalness" of buggy code. ICSE Baishakhi Ray, Vincent J. Hellendoorn, Saheel Godhane, Zhaopeng Tu, Alberto Bacchelli, Premkumar T. Devanbu
2015	—	`conf`	CACHECA: A Cache Language Model Based Code Suggestion Tool. ICSE (2) Christine Franks, Zhaopeng Tu, Premkumar T. Devanbu, Vincent J. Hellendoorn
2015	J	`jnl`	On the "Naturalness" of Buggy Code. CoRR Baishakhi Ray, Vincent J. Hellendoorn, Zhaopeng Tu, Connie Nguyen, Saheel Godhane, Alberto Bacchelli, Premkumar T. Devanbu
2015	A	`conf`	Will They Like This? Evaluating Code Contributions with Language Models. MSR Vincent J. Hellendoorn, Premkumar T. Devanbu, Alberto Bacchelli