Software Engineering (SELab)

@ HanKyong National University (HKNU)

Our News

[Now Recruiting] Call for Postdoctoral and Graduate Researchers: [View Intro PDF] [View Details]

우리 연구실은 성실하고 책임감있는 학/석사 연계과정, 석사과정, 박사후연구원을 모집합니다. 다양한 연구 기회를 탐색하고 더 자세한 정보를 원하시면, 양근석 교수님에게 문의하시거나 연구실 웹사이트를 방문해 주세요!
- 지능형 LLM 에이전트와 커뮤니티 협업 지식의 융합을 통한 최신 AI 기술/소프트웨어 개발 기술 연구
- sLLM을 활용한 소프트웨어 산출물 자동 생성 기술 연구
- sLLM을 활용한 소프트웨어 버그 패치 자동 생성 기술 연구
- sLLM을 기반 이슈 템플릿 자동화 및 협업 도구 통합 기술 개발
- sLLM을 DevSecOps를 활용한 코드 보안 이슈 탐지 및 보고 시스템 개발
- sLLM을 MLOps를 활용한 Kubernetes Cluster 구축 및 리소스 모니터링 시스템 개발
- 의료AI 및 금융AI에 적용한 sLLM 기반 데이터 자동 분석 및 보고 시스템 개발
※ 지원자가 소프트웨어 개발과 관련하여 별도의 관심 연구 분야를 가지고 있는 경우, 논의를 통해 결정합니다.

Join us at the 41st ACM Symposium on Applied Computing (SAC) in Thessaloniki, Greece, from March 23-27, 2026!

- Discover groundbreaking ideas and cutting-edge technologies at ACM SAC 2026. Connect with leading researchers and practitioners from around the world, attend insightful presentations, participate in interactive workshops, and network with peers in the beautiful setting of Thessaloniki. This is a unique opportunity to shape the future of applied computing. Don't miss out on the chance to be part of this prestigious event. [View Details]

[Notice] 사용자 중심 소프트웨어 서비스 개발 프로젝트 협력 환영

- SELAB@HKNU에서는 사용자 중심의 소프트웨어 서비스 연구 개발 프로젝트에 함께할 파트너를 기다리고 있습니다. 저희 연구실은 SW 개발/테스트 전문성과 함께 AI, 검색 증강 경량 거대 언어 모델 (RAG-sLLM), 검색 증강 경량 거대 멀티모달 모델 (RAG-sLMM), 빅데이터, 클라우드 기술, 정보시스템 감리 등 다양한 분야에서 뛰어난 전문 지식을 보유하고 있습니다.
- 특히, GS 인증, 감사 준비가 완료된 결과물, AI 서비스, 데이터 과학 분야에서 협력할 파트너를 찾고 있습니다. 저희와 함께 혁신적인 프로젝트(NIA / NIPA / IITP / 중기청 / K-Startup 등)를 성공적으로 이끌어갈 파트너를 찾고 있으니, 많은 관심과 문의 부탁드립니다.

[News] Our Recent Achievements
[2025-07-02] 우리 연구실에서 2025 한국컴퓨터종합학술대회의 소프트웨어공학 트랙에 정규 논문(학부 2학년 최서진, 유사 리포트 문맥 보강을 활용한 Retrieval-Augmented LLM 기반 버그 리포트 생성 기법, 제주ICC)을 발표 및 우수논문상을 수상하였습니다.
[2025-07-02] 우리 연구실에서 2025 한국컴퓨터종합학술대회의 소프트웨어공학 트랙에 정규 논문(학-석사 남규민, LLM 기반 오픈소스 소프트웨어 결함 위치 추정을 위한 AST 보강 의미 기반 검색 기법, 제주ICC)을 발표하였습니다.
[2025-07-02] 우리 연구실에서 2025 한국컴퓨터종합학술대회의 오픈소스소프트웨어 트랙에 포스터(학부 4학년 김낙균, Kubernetes 클러스터에서 리소스 제약이 etcd 성능에 미치는 영향, 제주ICC)을 발표하였습니다.
[2025-04-28] 우리 연구실에서 2025 IEEE Access(석사과정 Jinfeng Ji, Leveraging Cross-Project Similarity for Data Augmentation and Security Bug Report Prediction) SCIE 논문을 게재하였습니다.
[2024-12-20] 우리 연구실에서 2024 한국소프트웨어종합학술대회의 인공지능-소프트웨어공학 트랙에 정규 포스터(텍스트 유사도 기반 RAG와 sLLM을 활용한 소프트웨어 보안 버그 리포트 템플릿 생성 및 예측 기법, 여수EXPO)을 발표하였습니다.

Advancing RAG+sLLM and RAG+sLMM Research

AI-Driven Code Synthesis

At SELAB@HKNU, we are redefining software development through innovative tools powered by Retrieval-Augmented Generation (RAG) and specialized Large Language Models (sLLMs). Our custom-trained models leverage vast, diverse codebases to autonomously generate precise, context-aware code snippets that meet stringent industry standards and best practices. By automating intricate and repetitive coding tasks, our solutions significantly enhance development efficiency, reduce error rates, and enable engineers to concentrate on strategic, high-impact challenges.

Bridging Human Thought and Machine Logic

SELAB@HKNU is driving a paradigm shift in programming with RAG+sLLM-based natural language interfaces. These advanced systems allow developers to articulate programming intentions in plain English, seamlessly translating them into high-quality code. This capability not only streamlines workflows for experienced developers but also democratizes programming, lowering barriers for newcomers and fostering an inclusive, collaborative development ecosystem.

Transforming Code Documentation

Our RAG+sLLM solutions revolutionize code maintainability by automating the creation of comprehensive, real-time documentation. SELAB@HKNU's models generate detailed comments and structured documentation directly from codebases, eliminating manual, error-prone processes. This approach ensures that code remains well-documented, accessible, and ready for onboarding, dramatically improving project sustainability and team productivity.

A Multimodal Perspective on Code

SELAB@HKNU is reshaping how developers interact with and understand code through advancements in Large Multimodal Models (LMMs). By transforming code into dynamic visualizations, structural diagrams, and interactive representations, our tools provide unparalleled insights into complex architectures. This multimodal approach allows developers to rapidly diagnose issues, visualize dependencies, and collaborate with enhanced clarity, setting a new standard in code comprehension.

Visualizing Code Creation

Our cutting-edge LMM-powered tools revolutionize code generation by merging functional output with interactive visual elements like flowcharts and logic diagrams. This holistic view bridges the gap between textual code and its logical structure, making debugging, reviewing, and maintaining software more efficient. SELAB@HKNU's visual-first approach empowers developers to produce software of the highest quality with greater ease.

Next-Generation Debugging

SELAB@HKNU's state-of-the-art LMM solutions are redefining debugging processes by integrating multimodal artifacts, such as execution traces and logs, with advanced analysis capabilities. This approach enables precise error detection and intelligent fix recommendations, streamlining debugging workflows and proactively mitigating future issues. By enhancing debugging accuracy and efficiency, our tools empower developers to deliver more reliable and resilient software solutions.

Cultivating AI Talent in RAG+sLLM and RAG+sLMM

Small Large Language Models (sLLM)

At SELAB@HKNU, we are pioneering advanced methodologies for training and fine-tuning Small Large Language Models (sLLMs) on vast, high-quality code datasets. These models excel in generating precise code, completing complex snippets, translating across programming languages, and interpreting natural language instructions for diverse software development tasks. By pushing the boundaries of sLLM capabilities, we are setting new benchmarks in AI-driven software engineering, enabling more efficient and accurate development processes.

Large Multimodal Models (LMMs)

SELAB@HKNU is at the forefront of harnessing Large Multimodal Models (LMMs) to revolutionize how developers represent, interpret, and interact with code. By integrating multiple modalities—including text, images, and structural diagrams—our research advances multimodal code generation, completion, and debugging. This holistic approach unlocks deeper insights, enhances code comprehension, and improves functionality, driving innovation in AI-powered software engineering.

Retrieval-Augmented Generation (RAG)

SELAB@HKNU leads in developing advanced techniques for Retrieval-Augmented Generation (RAG), enabling models to dynamically integrate external knowledge into their processing workflows. This cutting-edge research enhances the ability of AI systems to deliver accurate, contextually rich responses for complex tasks in software engineering and multimodal content creation. Our work advances the precision and adaptability of AI, setting new standards in responsive, context-aware technology.

Big Data Techniques for Code Analysis

SELAB@HKNU employs state-of-the-art big data methodologies to analyze and process vast repositories of code, uncovering critical insights that drive advancements in RAG+sLLM and LMM technologies. By identifying key patterns, optimizations, and trends, we accelerate the development of intelligent, high-performance AI models designed for complex software engineering tasks.

Cloud-Native Techniques for Model Deployment

Our team at SELAB@HKNU leverages cutting-edge cloud-native technologies to design scalable, robust infrastructures for training, deploying, and managing RAG+sLLM and RAG+LMM models. These cloud-based solutions ensure seamless, reliable access for developers and researchers, streamlining integration and fostering innovation in AI-driven software development. Our commitment to efficient and scalable deployment enables organizations to achieve faster results with reduced operational complexity.

Open Source Contributions

SELAB@HKNU is deeply committed to advancing open-source RAG+sLLM and RAG+LMM initiatives, fostering a global ecosystem of collaboration and innovation. Through active contributions to the open-source community, we accelerate the development of state-of-the-art technologies, empowering developers and researchers worldwide to push the boundaries of AI-powered software engineering.

Frequently Asked Questions

1. Benefits for Our Researchers

Our lab provides an exceptional environment for graduate students to excel in practical AI, RAG+sLLM, RAG+sLMM, and advanced software development, preparing them as leaders in these fields. As a member of our team, you will:

- Develop Expertise in Applied AI: Gain hands-on experience and deep technical knowledge in using AI to automate software artifact generation through pioneering research and development projects.

- Engage in High-Impact Research: Contribute to advisor-led projects that push the boundaries of AI-driven applications in software engineering, aligned with your specific interests and expertise.

- Stay at the Forefront of Innovation: Attend national and international conferences and technical seminars, connecting with industry leaders and staying up-to-date on the latest advancements in AI and software engineering.

2. Supportive Lab Environment

Our lab cultivates a dynamic and collaborative research environment, emphasizing impactful outcomes and personalized growth for each researcher:

- Insightful Lab Meetings: Participate in engaging discussions on the latest advancements in AI, RAG+sLLM, RAG+sLMM, and their practical applications in software engineering, enhancing both knowledge and research acumen.

- Comprehensive Lab Seminars: Attend structured knowledge-sharing sessions to deepen your expertise in AI, RAG+sLLM, RAG+sLMM, and emerging trends in software engineering.

- Personalized Career Development Support: Benefit from one-on-one guidance tailored to your career goals, including preparation for coding assessments and interviews in AI and software engineering fields.

- Flexible, Results-Oriented Environment: Thrive in a flexible work culture that supports remote research, empowering you to focus on innovation and professional growth without traditional commuting constraints.

3. Our Vision

SELAB@HKNU is united by a vision to transform the software engineering landscape through groundbreaking AI-powered solutions:

- Pioneering Research Excellence: We are dedicated to conducting rigorous, pioneering research in applying AI, RAG+sLLM, and RAG+sLMM to software engineering, continually pushing the frontiers of knowledge and innovation.

- Cultivating World-Class Talent: Our mission is to develop the next generation of researchers and developers with the expertise, creativity, and vision to lead advancements in AI-driven software engineering.

- Driving Industry Transformation: We aspire to deliver high-impact solutions and foster thought leaders who will revolutionize the software engineering industry by harnessing AI, RAG+sLLM, and RAG+sLMM to enhance productivity, quality, and innovation.