98 citations · 287 across the 45 of their papers we have counts for
47 papers
Enabling Creative Exploration for Vibe Design Agents
Yifan Zhang, Nghi D. Q. Bui, Georgios Evangelopoulos +1
Vibe design agents translate natural-language requests into interfaces, yet repeated generations often converge on similar visual directions. We present an inference architecture t…
Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation
Minh Le-Anh, Nam Le Hai, Quyen Tran +4
Repository-level code generation requires generated code to be compatible not only with the target repository but also with its dependency environment. Existing retrieval-based met…
TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
Duc Nguyen, Sieu Tran, Hao Vo +6
Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propa…
GRAIN: Group Aggregation via Min-Norm Objective
Nghia Bui, Jiarui Yao, Lijing Wang
Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern deep learning: large models…
OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
Hao Vo, Phu Loc Nguyen, Khoa Vo +7
Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Auton…
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose pro…
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
Hao Vo, Khoa Vo, Phu Loc Nguyen +10
Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity acros…
Documentation-Guided Agentic Codebase Migration from C to Rust
Minh Le-Anh, Anh Nguyen Hoang, Bach Le +1
Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss architectural intent. We pr…
Agentic Coding Needs Proactivity, Not Just Autonomy
Nghi D. Q. Bui, Georgios Evangelopoulos
Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to…
COBOL-Coder: Domain-Adapted Large Language Models for COBOL Code Generation and Translation
Anh T. V. Dau, Shin Hwei Tan, Jinqiu Yang +2
COBOL remains a critical language for mainframe systems, yet existing large language models (LLMs) struggle to generate and translate COBOL code correctly. This paper reports our e…
COBOLAssist: Analyzing and Fixing Compilation Errors for LLM-Powered COBOL Code Generation
Anh T. V. Dau, Shin Hwei Tan, Jinqiu Yang +2
Legacy programming languages such as COBOL (Common Business-Oriented Language) remain critical in business computing. However, maintaining legacy COBOL systems is increasingly chal…
CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models
Khoa Vo, Sieu Tran, Taisei Hanyu +8
Vision-Language-Action (VLA) models promise generalist robot manipulation, but are typically trained and deployed as short-horizon policies that assume the latest observation is su…
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
Nghi D. Q. Bui
The landscape of AI coding assistance is undergoing a fundamental shift from complex IDE plugins to versatile, terminal-native agents. Operating directly where developers manage so…
Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond
Minh Le-Anh, Huyen Nguyen, Khanh An Tran +4
Large language models for code (CodeLLMs) have demonstrated remarkable success in standalone code completion and generation, sometimes even surpassing human performance, yet their…
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
Tue Le, Minh V. T. Thai, Dung Nguyen Manh +2
Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-ho…
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
Anh Nguyen Hoang, Minh Le-Anh, Bach Le +1
Given a large and evolving codebase, the ability to automatically generate holistic, architecture-aware documentation that captures not only individual functions but also cross-fil…
On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating
Huy Nguyen, Thong T. Doan, Quang Pham +3
Mixture of experts (MoE) methods are a key component in most large language model architectures, including the recent series of DeepSeek models. Compared to other MoE implementatio…
SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs
Minh V. T. Pham, Huy N. Phan, Hoang N. Phan +3
Large language models (LLMs) are transforming automated program repair (APR) through agent-based approaches that localize bugs, generate patches, and verify fixes. However, the lac…
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
Cuong Chi Le, Hoang-Chau Truong-Vinh, Huy Nhat Phan +3
Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for cod…
CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs
Dung Nguyen Manh, Thang Phan Chau, Nam Le Hai +4
Recent advances in Code Large Language Models (CodeLLMs) have primarily focused on open-ended code generation, often overlooking the crucial aspect of code understanding and reason…
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Huy Nhat Phan, Tien N. Nguyen, Phong X. Nguyen +1
Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled…
XMainframe: A Large Language Model for Mainframe Modernization
Anh T. V. Dau, Hieu Trung Dao, Anh Tuan Nguyen +3
Mainframe operating systems, despite their inception in the 1940s, continue to support critical sectors like finance and government. However, these systems are often viewed as outd…
Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation
Nam Le Hai, Nghi D. Q. Bui
Code comments provide important information for understanding the source code. They can help developers understand the overall purpose of a function or class, as well as identify b…
CodeFlow: Program Behavior Prediction with Dynamic Dependencies Learning
Cuong Chi Le, Hoang Nhat Phan, Huy Nhat Phan +2
Predicting program behavior without execution is a critical task in software engineering. Existing models often fall short in capturing the dynamic dependencies among program eleme…