Prem Devanbu
University of California, Davis
H-index: 66
North America-United States
Top articles of Prem Devanbu
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Automatic semantic augmentation of language model prompts (for code summarization) | Toufique Ahmed Kunal Suresh Pai Premkumar Devanbu Earl T Barr | 2024/3/6 | |
Studying LLM Performance on Closed-and Open-source Data | arXiv preprint arXiv:2402.15100 | Toufique Ahmed Christian Bird Premkumar Devanbu Saikat Chakraborty | 2024/2/23 |
Quality and Trust in LLM-generated Code | arXiv preprint arXiv:2402.02047 | Claudio Spiess David Gros Kunal Suresh Pai Michael Pradel Md Rafiqul Islam Rabin | 2024/2/3 |
Enhancing Trust in LLM-Generated Code Summaries with Calibrated Confidence Scores | arXiv preprint arXiv:2404.19318 | Yuvraj Virk Premkumar Devanbu Toufique Ahmed | 2024/4/30 |
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair | arXiv preprint arXiv:2403.17134 | Islem Bouzenia Premkumar Devanbu Michael Pradel | 2024/3/25 |
Large language models and simple, stupid bugs | Kevin Jesse Toufique Ahmed Premkumar T Devanbu Emily Morgan | 2023/5/15 | |
A survey of trojans in neural models of source code: Taxonomy and techniques | arXiv preprint arXiv:2305.03803 | Aftab Hussain Md Rafiqul Islam Rabin Toufique Ahmed Bowen Xu Prem Devanbu | 2023/5/5 |
AI Safety Subproblems for Software Engineering Researchers | arXiv preprint arXiv:2304.14597 | David Gros Prem Devanbu Zhou Yu | 2023/4/28 |
Extending source code pre-trained language models to summarise decompiled binarie | Ali Al-Kaswan Toufique Ahmed Maliheh Izadi Anand Ashok Sawant Premkumar Devanbu | 2023/3/21 | |
Better patching using LLM prompting, via Self-Consistency | Toufique Ahmed Premkumar Devanbu | 2023/9/11 | |
Towards Understanding What Code Language Models Learned | arXiv preprint arXiv:2306.11943 | Toufique Ahmed Dian Yu Chengxuan Huang Cathy Wang Prem Devanbu | 2023/6/20 |
FlexType: a plug-and-play framework for type inference models | Sivani Voruganti Kevin Jesse Premkumar Devanbu | 2022/10/10 | |
Multilingual training for software engineering | Toufique Ahmed Premkumar Devanbu | 2022/5/21 | |
SynShine: Improved Fixing of Syntax Errors | IEEE Transactions on Software Engineering | Toufique Ahmed Noah Rose Ledesma Premkumar Devanbu | 2022/10/10 |
Naturalness and Artifice of Code: Exploiting the Bi-Modality | Premkumar Devanbu | 2022/2/24 | |
Few-shot training llms for project-specific code-summarization | Toufique Ahmed Premkumar Devanbu | 2022/10/10 | |
Learning code summarization from a small and local dataset | arXiv preprint arXiv:2206.00804 | Toufique Ahmed Premkumar Devanbu | 2022/6/2 |
Learning to predict user-defined types | IEEE Transactions on Software Engineering | Kevin Jesse Premkumar T Devanbu Anand Sawant | 2022/5/30 |
Natgen: generative pre-training by “naturalizing” source code | Saikat Chakraborty Toufique Ahmed Yangruibo Ding Premkumar T Devanbu Baishakhi Ray | 2022/11/7 | |
Manytypes4typescript: A comprehensive typescript dataset for sequence-based type inference | Kevin Jesse Premkumar T Devanbu | 2022/5/23 |