Nghi D. Q. Bui

58 papers A* 8Journal 35Unranked 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned.
CoRR
Nghi D. Q. Bui
2026 J jnl
Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond.
CoRR
Minh Le-Anh, Huyen Nguyen, Khanh An Tran, Nam Le Hai, Linh Ngo Van, Nghi D. Q. Bui, Bach Le
2025 — conf
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology.
Forge@ICSE
Minh Huynh Nguyen, Thang Phan Chau, Phong X. Nguyen, Nghi D. Q. Bui
2025 — conf
CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning.
Forge@ICSE
Cuong Chi Le, Hoang Nhat Phan, Huy Nhat Phan, Tien N. Nguyen, Nghi D. Q. Bui
2025 A* conf
CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs.
ICLR
Dung Manh Nguyen, Thang Chau Phan, Nam Le Hai, Tien-Thong Doan, Nam V. Nguyen, Quang Pham, Nghi D. Q. Bui
2025 J jnl
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases.
CoRR
Anh Nguyen Hoang, Minh Le-Anh, Bach Le, Nghi D. Q. Bui
2025 J jnl
On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating.
CoRR
Huy Nguyen, Thong T. Doan, Quang Pham, Nghi D. Q. Bui, Nhat Ho, Alessandro Rinaldo
2025 — conf
On the Impacts of Contexts on Repository-Level Code Generation.
NAACL (Findings)
Nam Le Hai, Dung Manh Nguyen, Nghi D. Q. Bui
2025 — conf
RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion.
Forge@ICSE
Huy Nhat Phan, Hoang Nhat Phan, Tien N. Nguyen, Nghi D. Q. Bui
2025 J jnl
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios.
CoRR
Minh V. T. Thai, Tue Le, Dung Nguyen Manh, Huy Phan Nhat, Nghi D. Q. Bui
2025 J jnl
SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs.
CoRR
Minh V. T. Pham, Huy Nhat Phan, Hoang Nhat Phan, Cuong Chi Le, Tien N. Nguyen, Nghi D. Q. Bui
2025 J jnl
Token-Regulated Group Relative Policy Optimization for Stable Reinforcement Learning in Large Language Models.
CoRR
Tue Le, Nghi D. Q. Bui, Linh Ngo Van, Trung Le
2025 — conf
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning.
NAACL (Findings)
Cuong Chi Le, Hoang Chau Truong Vinh, Huy Nhat Phan, Dung Duy Le, Tien N. Nguyen, Nghi D. Q. Bui
2024 J jnl
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology.
CoRR
Minh Huynh Nguyen, Thang Phan Chau, Phong X. Nguyen, Nghi D. Q. Bui
2024 J jnl
CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs.
CoRR
Dung Nguyen Manh, Thang Phan Chau, Nam Le Hai, Thong T. Doan, Nam V. Nguyen, Quang Pham, Nghi D. Q. Bui
2024 — conf
DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies.
EACL (Demonstrations)
Anh Dau, Jin L. C. Guo, Nghi D. Q. Bui
2024 — conf
Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation.
NLBSE@ICSE
Nam Le Hai, Nghi D. Q. Bui
2024 J jnl
Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation.
CoRR
Nam Le Hai, Nghi D. Q. Bui
2024 — conf
Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals.
IDE@ICSE
Khanh Nghiem, Anh Minh Nguyen, Nghi D. Q. Bui
2024 J jnl
Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals.
CoRR
Khanh Nghiem, Anh Minh Nguyen, Nghi D. Q. Bui
2024 J jnl
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale.
CoRR
Huy Nhat Phan, Phong X. Nguyen, Nghi D. Q. Bui
2024 J jnl
Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs.
CoRR
Cuong Chi Le, Hoang Nhat Phan, Huy Nhat Phan, Tien N. Nguyen, Nghi D. Q. Bui
2024 J jnl
REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark.
CoRR
Nam Le Hai, Dung Manh Nguyen, Nghi D. Q. Bui
2024 J jnl
RepoHyper: Better Context Retrieval Is All You Need for Repository-Level Code Completion.
CoRR
Huy Nhat Phan, Hoang Nhat Phan, Tien N. Nguyen, Nghi D. Q. Bui
2024 J jnl
VISUALCODER: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning.
CoRR
Cuong Chi Le, Hoang Chau Truong Vinh, Huy Nhat Phan, Dung Duy Le, Tien N. Nguyen, Nghi D. Q. Bui
2024 J jnl
XMainframe: A Large Language Model for Mainframe Modernization.
CoRR
Anh T. V. Dau, Hieu Trung Dao, Anh Tuan Nguyen, Hieu Trung Tran, Phong X. Nguyen, Nghi D. Q. Bui
2023 — conf
Better Language Models of Code through Self-Improvement.
ACL (Findings)
Hung Quoc To, Nghi D. Q. Bui, Jin L. C. Guo, Tien N. Nguyen
2023 J jnl
Better Language Models of Code through Self-Improvement.
CoRR
Hung Quoc To, Nghi D. Q. Bui, Jin Guo, Tien N. Nguyen
2023 J jnl
Bootstrapping Code-Text Pretrained Language Model to Detect Inconsistency Between Code and Comment.
CoRR
Anh T. V. Dau, Nghi D. Q. Bui, Jin L. C. Guo
2023 — conf
Class based Influence Functions for Error Detection.
ACL (2)
Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Huu-Tien Dang, Hieu Nguyen, Anh T. V. Dau, Nghi D. Q. Bui
2023 J jnl
Class based Influence Functions for Error Detection.
CoRR
Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Huu-Tien Dang, Hieu Ngoc Nguyen, Anh T. V. Dau, Nghi D. Q. Bui
2023 A* conf
CodeT5+: Open Code Large Language Models for Code Understanding and Generation.
EMNLP
Yue Wang, Hung Le, Akhilesh Gotmare, Nghi D. Q. Bui, Junnan Li, Steven C. H. Hoi
2023 J jnl
CodeT5+: Open Code Large Language Models for Code Understanding and Generation.
CoRR
Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D. Q. Bui, Junnan Li, Steven C. H. Hoi
2023 J jnl
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM.
CoRR
Nghi D. Q. Bui, Hung Le, Yue Wang, Junnan Li, Akhilesh Deepak Gotmare, Steven C. H. Hoi
2023 J jnl
Neural Rankers for Code Generation via Inter-Cluster Modeling.
CoRR
Hung Quoc To, Minh Huynh Nguyen, Nghi D. Q. Bui
2023 — conf
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation.
EMNLP (Findings)
Dung Nguyen Manh, Le Nam Hai, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin Guo, Nghi D. Q. Bui
2023 J jnl
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation.
CoRR
Dung Nguyen Manh, Nam Le Hai, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin Guo, Nghi D. Q. Bui
2022 J jnl
Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5.
CoRR
Nghi D. Q. Bui, Yue Wang, Steven Hoi
2022 J jnl
Learning to Represent Programs with Code Hierarchies.
CoRR
Minh Nguyen, Nghi D. Q. Bui
2022 A* conf
Towards Robust Models of Code via Energy-Based Learning on Auxiliary Datasets.
ASE
Nghi D. Q. Bui, Yijun Yu
2022 J jnl
Towards Using Data-Centric Approach for Better Code Representation Learning.
CoRR
Anh Dau, Thang Nguyen-Duc, Hoang Thanh-Tung, Nghi D. Q. Bui
2022 A* conf
Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora.
ASE
Anh T. V. Dau, Nghi D. Q. Bui, Thang Nguyen-Duc, Hoang Thanh-Tung
2021 A* conf
InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees.
ICSE
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2021 J jnl
On the generalizability of Neural Program Models with respect to semantic-preserving program transformations.
Inf. Softw. Technol.
Md. Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang, Yijun Yu, Lingxiao Jiang, Mohammad Amin Alipour
2021 A* conf
Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations.
SIGIR
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2021 A* conf
TreeCaps: Tree-Based Capsule Networks for Source Code Processing.
AAAI
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2020 J jnl
Efficient Framework for Learning Code Representations through Semantic-Preserving Program Transformations.
CoRR
Nghi D. Q. Bui
2020 J jnl
InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees.
CoRR
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2020 J jnl
On the Generalizability of Neural Program Analyzers with respect to Semantic-Preserving Program Transformations.
CoRR
Md. Rafiqul Islam Rabin, Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang, Mohammad Amin Alipour
2020 J jnl
TreeCaps: Tree-Based Capsule Networks for Source Code Processing.
CoRR
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2019 A* conf
AutoFocus: Interpreting Attention-Based Neural Networks by Code Perturbation.
ASE
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2019 J jnl
SAR: Learning Cross-Language API Mappings with Little Knowledge.
CoRR
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2019 — conf
SAR: learning cross-language API mappings with little knowledge.
ESEC/SIGSOFT FSE
Nghi D. Q. Bui, Yijun Yu, Lingxiao Jiang
2019 — conf
Towards zero knowledge learning for cross language API mappings.
ICSE (Companion Volume)
Nghi D. Q. Bui
2018 — conf
Cross-Language Learning for Program Classification Using Bilateral Tree-Based Convolutional Neural Networks.
AAAI Workshops
Nghi D. Q. Bui, Lingxiao Jiang, Yijun Yu
2018 J jnl
Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code.
CoRR
Nghi D. Q. Bui, Lingxiao Jiang
2018 — conf
Hierarchical learning of cross-language mappings through distributed vector representations for code.
ICSE (NIER)
Nghi D. Q. Bui, Lingxiao Jiang
2017 J jnl
Cross-Language Learning for Program Classification using Bilateral Tree-Based Convolutional Neural Networks.
CoRR
Nghi D. Q. Bui, Lingixao Jiang, Yijun Yu