# CSI-Agent Group — full site content

> Everything on https://csiagentgroup.com/ in one document: members, publications, projects and news of the CSI-Agent Group at Sungkyunkwan University (SKKU). Generated from the site's data on 2026-10-05. Start from [llms.txt](https://csiagentgroup.com/llms.txt) for an overview.

## People

Source: https://csiagentgroup.com/people/

### Faculty

- **Honguk Woo (우홍욱)** — Professor, Lab Director. Research: Embodied Agent, Physical AI, Reinforcement Learning, Machine Learning. [Google Scholar](https://scholar.google.com/citations?user=Gaxjc7UAAAAJ&hl=en)

### Ph.D. students

- **Youngseok Lee (이영석)** — Ph.D Candidate, Robot team. Research: Network Optimization, Intelligent System, Machine Learning. [Google Scholar](https://scholar.google.com/citations?hl=ko&user=GhwtxtgAAAAJ&view_op=list_works&sortby=pubdate)
- **Woo Kyung Kim (김우경)** — Ph.D Candidate, Team Leader, Robot team. Research: Reinforcement Learning, Skill Diffusion, Physical AI. [Google Scholar](https://scholar.google.co.kr/citations?user=OFFacb0AAAAJ&hl=en), [Website](https://kwk2696.github.io/)
- **Wonje Choi (최원제)** — Ph.D Candidate, Team Leader, World Model team. Research: Embodied Agent, Neuro-Symbolic AI, Agent Memory. [Google Scholar](https://scholar.google.co.kr/citations?user=L4d1CjEAAAAJ&hl=en)
- **Minjong Yoo (유민종)** — Ph.D Candidate, Team Leader, Robot team. Research: Reinforcement Learning. [Google Scholar](https://scholar.google.co.kr/citations?user=O6L-PkgAAAAJ&hl=en)
- **Hyungseong Na (나현승)** — Ph.D Candidate, Robot team. Research: Reinforcement Learning, Machine Learning, Natural Language Process.
- **Daehee Lee (이대희)** — Ph.D Candidate, Team Leader, World Model team. Research: Lifelong Learning Agents, Continual Learning, Reinforcement Learning. [Google Scholar](https://scholar.google.co.kr/citations?user=llB3SucAAAAJ), [Website](https://l2dulgi.github.io/)
- **Jinwoo Jang (장진우)** — Ph.D Student, Team Leader, World Model team. Research: Large Language Model, Embodied Agent. [Google Scholar](https://scholar.google.co.kr/citations?user=3rewAQIAAAAJ&hl=en&oi=ao), [Website](https://doldam0.github.io/)
- **Saehun Chun (천세헌)** — Ph.D Student, World Model team. Research: Agentic Workflow, Serving System, System for AI. [Google Scholar](https://scholar.google.com/citations?user=v-aLlUsAAAAJ&hl=en)
- **Sihyung Yoon (윤시형)** — Ph.D Student, Team Leader, Robot team. Research: Large Language Model. [Google Scholar](https://scholar.google.com/citations?user=QUOnWbkAAAAJ&hl=en)
- **Sera Choi (최세라)** — Ph.D Student, World Model team. Research: Large Language Model. [Google Scholar](https://scholar.google.com/citations?hl=en&user=nlk4ii0AAAAJ)
- **Younguk Song (송영욱)** — Ph.D Student, World Model team. Research: Embodied Agent.
- **Hyunsuk Cho (조현석)** — Ph.D Student, Robot team. Research: Large Language Model.
- **Seungchan An (안승찬)** — Ph.D Student, Robot team. Research: Robot.
- **Mingyo Hong (홍민교)** — Ph.D Student, World Model team. Research: Large Language Model, Agentic AI.
- **Junhwan Jeong (정준환)** — Ph.D Student, Robot team. Research: Robot.

### M.S. students

- **Jooyoung Kim (김주영)** — M.S. Student, World Model team. Research: Embodied Agent. [Google Scholar](https://scholar.google.co.kr/citations?hl=en&user=tRSSQlUAAAAJ)
- **Soyoung Kim (김소영)** — M.S. Student, World Model team. Research: Multi Agent Systems, Agentic AI.
- **TaeYoon Kwack (곽태윤)** — M.S. Student, Robot team. Research: Robot.
- **Junyong Lee (이준용)** — M.S. Student, Robot team. Research: Robot.
- **Jisoo Kim (김지수)** — M.S. Student, Robot team. Research: Robot.
- **GyeongHo Min (민경호)** — M.S. Student, Robot team. Research: Robot.
- **Eunyoung Park (박은영)** — M.S. Student, Robot team. Research: Robot.
- **Daniel J. Rho (노정호)** — M.S. Student, World Model team. Research: World Model.
- **Gyuri Lee (이규리)** — M.S. Student, Robot team. Research: Robot.
- **Seojeong Choi (최서정)** — M.S. Student, Robot team. Research: Robot. [Google Scholar](https://scholar.google.com/citations?user=ze6ejocAAAAJ&hl=ko&oi=sra)
- **Jae Jun Kim (김재준)** — M.S. Student, Robot team. Research: Robot.

### Undergraduate researchers

- **Yuri Park (박유리)** — Senior, Robot team. Research: Robot.
- **Joowan Chae (채주완)** — Senior, Robot team. Research: Robot.

### On leave

- **Sanghyun Ahn (안상현)** — M.S. Student, currently CMU Visiting Scholar. Research: Large Language Model, Neuro Symbolic AI, Embodied Agent. [Google Scholar](https://scholar.google.co.kr/citations?user=xGh7hdIAAAAJ&hl=en)
- **Seunghwan Jeong (정승환)** — Ph.D Candidate, currently Acryl.

### Alumni

- **Suin Lee (이수인)** — M.S. 2021.03, now at Kakao
- **Hyunsung Lee (이현성)** — M.S. 2021.08, now at Spellbrush
- **Minjae Park (박민재)** — B.S. 2022.03, now at CS@KAIST
- **SungHyun Choi (최성현)** — M.S. 2022.08, now at LG CNS
- **Ju-eun Park (박주은)** — M.S. 2022.08, now at Line
- **Jooyoung Park (박주영)** — M.S. 2022.08, now at Technical Research Personnel
- **Yunho Kim (김윤호)** — M.S. 2022.08, now at Technical Research Personnel
- **Donghoon Kim (김동훈)** — M.S. 2024.02, now at Samsung
- **Jihye Ok (옥지혜)** — M.S. 2024.08, now at Acryl
- **Jaehyun Song (송재현)** — M.S. 2024.08, now at DEEPX
- **Sangwoo Shin (신상우)** — M.S. 2024.08, now at Ph.D. Student at University of Wisconsin-Madison
- **Yujeong Lee (이유정)** — M.S. 2025.02, now at KIA
- **Yooseong Kang (강유성)** — M.S. 2025.08
- **Jinwoo Park (박진우)** — M.S. 2025.08, now at DIDEN ROBOTICS
- **SeungHyun Kim (김승현)** — M.S. 2025.08, now at POSCO
- **Minjong Yoo (유민종)** — Ph.D. 2025.08, now at Samsung Research
- **Jongmoon Jun (전종문)** — M.S. 2026.06
- **Gwangpyo Yoo (유광표)** — Ph.D. 2026.08, now at ROBROS

## Publications

Source: https://csiagentgroup.com/publications/

### 2026

- HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse — Saehun Chun, Wonje Choi, Jinwoo Jang, TaeYoon Kwack, Honguk Woo. *NeurIPS 2026 (oral)*
- NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents — Wonje Choi, Jooyoung Kim, Sera Choi, Younguk Song, Honguk Woo. *NeurIPS 2026 (spotlight)*
- Skill-Adaptive Noise Scheduling for Diffusion Policies — Woo Kyung Kim, Gwangpyo Yoo, Eunyoung Park, Honguk Woo. *NeurIPS 2026*
- Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation — Daehee Lee, Dongsu Lee, Sanghyun Ahn, Minjong Yoo, Honguk Woo. *NeurIPS 2026*
- Visual Compliance via Executable Safety Rule Entailment — Jisoo Kim, TaeYoon Kwack, Jinwoo Jang, Honguk Woo. *EMNLP 2026* — [arXiv](https://arxiv.org/abs/2609.18328)
- MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing — Junyong Lee, Woo Kyung Kim, Honguk Woo. *EMNLP 2026*
- ParentingLLM: Pacing Reasoning Maturity for Bidirectional Test-Time Scaling under Token Budgets — Seunghwan Jeong, Sugi Lee, Wei-Jin Park, Ikjun Yeom, Honguk Woo. *EMNLP 2026*
- Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code — Jisoo Kim, TaeYoon Kwack, Jinwoo Jang, Woo Kyung Kim, Honguk Woo. *CIKM 2026* — [arXiv](https://arxiv.org/abs/2609.19199)
- Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments — Jinwoo Jang, Daniel J. Rho, Sihyung Yoon, Hyunsuk Cho, Honguk Woo. *ECCV 2026* — [arXiv](https://arxiv.org/abs/2607.00457)
- RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents — Sihyung Yoon, Minjong Yoo, Sanghyun Ahn, Seojeong Choi, Honguk Woo. *IROS 2026* — [arXiv](https://arxiv.org/abs/2607.27881)
- Knothe-Rosenblatt Quantile Regression for Risk-sensitive Multi-objective Reinforcement Learning — Gwangpyo Yoo, Woo Kyung Kim, Honguk Woo. *ICML 2026* — [OpenReview](https://openreview.net/forum?id=gGx6DyI6Xv)
- Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents — Saehun Chun, Wonje Choi, Sera Choi, Sanghyun Ahn, Honguk Woo. *ICML 2026* — [arXiv](https://arxiv.org/abs/2606.13097), [OpenReview](https://openreview.net/forum?id=hkmpUHQxgv)
- Efficient Skill Grounding via Code Refactoring with Small Language Models — Sera Choi, Wonje Choi, Saehun Chun, Daehee Lee, Jooyoung Kim, Chaeun Lee, Honguk Woo. *ICML 2026* — [arXiv](https://arxiv.org/abs/2606.07999), [OpenReview](https://openreview.net/forum?id=GQ4zj5YiyC)
- Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning — Jooyoung Kim, Wonje Choi, Younguk Song, Honguk Woo. *CVPR 2026* — [arXiv](https://arxiv.org/abs/2603.18495)
- Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments — Jinwoo Jang, Minjong Yoo, Sihyung Yoon, Honguk Woo. *ICLR 2026* — [arXiv](https://arxiv.org/abs/2601.22647), [OpenReview](https://openreview.net/forum?id=LQD1MrnbxH), [Code](https://github.com/doldam0/tmow)

### 2025

- Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning — Sanghyun Ahn, Wonje Choi, Junyong Lee, Jinwoo Park, Honguk Woo. *NeurIPS 2025 (spotlight)* — [arXiv](https://arxiv.org/abs/2510.21302), [OpenReview](https://openreview.net/forum?id=VaC4sa96EI)
- Policy Compatible Skill Incremental Learning via Lazy Learning Interface — Daehee Lee, Dongsu Lee, TaeYoon Kwack, Wonje Choi, Honguk Woo. *NeurIPS 2025 (spotlight)* — [arXiv](https://arxiv.org/abs/2509.20612), [OpenReview](https://openreview.net/forum?id=xmYT1JqVpj), [Code](https://github.com/L2dulgi/SIL-C)
- NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning — Wonje Choi, Jooyoung Kim, Honguk Woo. *NeurIPS 2025* — [arXiv](https://arxiv.org/abs/2510.19429), [OpenReview](https://openreview.net/forum?id=a8sJEH4Cjb)
- World Model Implanting for Test-time Adaptation of Embodied Agents — Minjong Yoo, Jinwoo Jang, Sihyung Yoon, Honguk Woo. *ICML 2025* — [arXiv](https://arxiv.org/abs/2509.03956), [OpenReview](https://openreview.net/forum?id=tpbtodnI1p), [Code](https://github.com/mjyoo2/WorMI)
- NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains — Wonje Choi, Jinwoo Park, Sanghyun Ahn, Daehee Lee, Honguk Woo. *ICLR 2025* — [OpenReview](https://openreview.net/forum?id=VoayJihXra)
- Model Risk-sensitive Offline Reinforcement Learning — Gwangpyo Yoo, Honguk Woo. *ICLR 2025* — [OpenReview](https://openreview.net/forum?id=h6k4809xVV)
- In-Context Policy Adaptation via Cross-Domain Skill Diffusion — Minjong Yoo, Woo Kyung Kim, Honguk Woo. *AAAI 2025* — [arXiv](https://arxiv.org/abs/2509.04535), [DOI](https://doi.org/10.1609/aaai.v39i21.34373)

### 2024

- Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation — Daehee Lee, Minjong Yoo, Woo Kyung Kim, Wonje Choi, Honguk Woo. *NeurIPS 2024* — [arXiv](https://arxiv.org/abs/2410.22658), [OpenReview](https://openreview.net/forum?id=RcPAJAnpnm), [Code](https://github.com/L2dulgi/IsCiL)
- LLM-based Skill Diffusion for Zero-shot Policy Adaptation — Woo Kyung Kim, Youngseok Lee, Jooyoung Kim, Honguk Woo. *NeurIPS 2024* — [OpenReview](https://openreview.net/forum?id=UGlDVc0GTU)
- Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following — Minjong Yoo, Jinwoo Jang, Wei-Jin Park, Honguk Woo. *NeurIPS 2024* — [arXiv](https://arxiv.org/abs/2509.08222), [OpenReview](https://openreview.net/forum?id=LpXV29Ggl3)
- LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble — Yujeong Lee, Sangwoo Shin, Wei-Jin Park, Honguk Woo. *EMNLP Findings 2024* — [arXiv](https://arxiv.org/abs/2411.17135), [DOI](https://doi.org/10.18653/v1/2024.findings-emnlp.170)
- Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments — Sangwoo Shin, SeungHyun Kim, Youngsoo Jang, Moontae Lee, Honguk Woo. *ACL Findings 2024* — [arXiv](https://arxiv.org/abs/2408.01024), [DOI](https://doi.org/10.18653/v1/2024.findings-acl.200)
- Embodied CoT Distillation From LLM To Off-the-shelf Agents — Wonje Choi, Woo Kyung Kim, Minjong Yoo, Honguk Woo. *ICML 2024* — [arXiv](https://arxiv.org/abs/2412.11499), [OpenReview](https://openreview.net/forum?id=M4Htd52HMH)
- Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks — Donghoon Kim, Minjong Yoo, Honguk Woo. *IJCAI 2024* — [arXiv](https://arxiv.org/abs/2408.11300), [DOI](https://doi.org/10.24963/ijcai.2024/473)
- Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation — Woo Kyung Kim, Minjong Yoo, Honguk Woo. *IJCAI 2024* — [arXiv](https://arxiv.org/abs/2408.12110), [DOI](https://doi.org/10.24963/ijcai.2024/475)
- Model Adaptation for Time Constrained Embodied Control — Jaehyun Song, Minjong Yoo, Honguk Woo. *CVPR 2024* — [arXiv](https://arxiv.org/abs/2406.11128)
- Robust Policy Learning via Offline Skill Diffusion — Woo Kyung Kim, Minjong Yoo, Honguk Woo. *AAAI 2024* — [arXiv](https://arxiv.org/abs/2403.00225), [DOI](https://doi.org/10.1609/aaai.v38i12.29217)
- Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures — Gwangpyo Yoo, Jinwoo Park, Honguk Woo. *AAAI 2024* — [DOI](https://doi.org/10.1609/aaai.v38i15.29589)
- SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation — Sangwoo Shin, Minjong Yoo, Jeongwoo Lee, Honguk Woo. *AAAI 2024* — [arXiv](https://arxiv.org/abs/2402.07418), [DOI](https://doi.org/10.1609/aaai.v38i13.29421)

### 2023

- Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents — Wonje Choi, Woo Kyung Kim, SeungHyun Kim, Honguk Woo. *NeurIPS 2023* — [arXiv](https://arxiv.org/abs/2412.11484), [OpenReview](https://openreview.net/forum?id=Ny3GcHLyzj)
- One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill — Sangwoo Shin, Daehee Lee, Minjong Yoo, Woo Kyung Kim, Honguk Woo. *ICML 2023* — [arXiv](https://arxiv.org/abs/2402.08369), [OpenReview](https://openreview.net/forum?id=pmUI642icm)
- A Configurable Model-Based Reinforcement Learning Framework for Disaggregated Storage Systems — Seunghwan Jeong, Honguk Woo. *IEEE Access 2023* — [DOI](https://doi.org/10.1109/ACCESS.2023.3244388)
- A Maturity Model for Trustworthy AI Software Development — Seunghwan Cho, Ingyu Kim, Jinhan Kim, Honguk Woo, Wanseon Shin. *Applied Sciences 2023* — [DOI](https://doi.org/10.3390/app13084771)

### 2022

- Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning — Minjong Yoo, SangWoo Cho, Honguk Woo. *NeurIPS 2022 (oral)* — [arXiv](https://arxiv.org/abs/2408.15593)
- Federated Offline Reinforcement Learning for Autonomous Systems — Ju-eun Park, Honguk Woo. *CCCE 2022* — [DOI](https://doi.org/10.1007/978-3-031-17422-3_10)
- Sample-Efficient Deep Learning Techniques for Burn Severity Assessment with Limited Data Conditions — Hyunkyung Shin, Hyeonung Shin, Wonje Choi, Jaesung Park, Minjae Park, Euiyul Koh, Honguk Woo. *Applied Sciences 2022* — [DOI](https://doi.org/10.3390/app12147317)
- Toward an Effective Bug Triage System Using Transformers to Add New Developers — Syed Farhan Alam Zaidi, Honguk Woo, Chan-Gun Lee. *Journal of Sensors 2022* — [DOI](https://doi.org/10.1155/2022/4347004)
- Integrating A Deep Learning-based Plane Detector in Mobile AR Systems for Improvement of Plane Detection — Yunho Kim, Honguk Woo. *2022 the 8th International Conference on Computing and Artificial Intelligence (ICCAI) 2022* — [DOI](https://doi.org/10.1145/3532213.3532304)
- A Graph Convolution Network-Based Bug Triage System to Learn Heterogeneous Graph Representation of Bug Reports — Syed Farhan Alam Zaidi, Honguk Woo, Chan-Gun Lee. *IEEE Access 2022* — [DOI](https://doi.org/10.1109/ACCESS.2022.3153075)
- Transfer Learning based Precise Pose Estimation with Insufficient Data — Wonje Choi, Honguk Woo. *2022 the 5th International Conference on Machine Vision and Applications (ICMVA) 2022* — [DOI](https://doi.org/10.1145/3523111.3523118)
- Iterative Pruning-based Model Compression for Pose Estimation on Resource-constrained Devices — SungHyun Choi, Wonje Choi, Youngseok Lee, Honguk Woo. *2022 the 5th International Conference on Machine Vision and Applications (ICMVA) 2022* — [DOI](https://doi.org/10.1145/3523111.3523128)
- Mean-variance Based Risk-sensitive Reinforcement Learning with Interpretable Attention — Woo Kyung Kim, Youngseok Lee, Honguk Woo. *2022 the 5th International Conference on Machine Vision and Applications(ICMVA) 2022* — [DOI](https://doi.org/10.1145/3523111.3523127)
- Reinforcement Learning based Load Balancing in a Distributed Heterogeneous Storage System — Jooyoung Park, Seunghwan Jeong, Honguk Woo. *International Conference on Information Networking (ICOIN) 2022* — [DOI](https://doi.org/10.1109/ICOIN53446.2022.9687277)
- Structure Learning-Based Task Decomposition for Reinforcement Learning in Non-stationary Environments — Honguk Woo, Gwangpyo Yoo, Minjong Yoo. *AAAI 2022* — [DOI](https://doi.org/10.1609/aaai.v36i8.20844)
- An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation — Honguk Woo, Hyunsung Lee, Sangwoo Cho. *AAAI 2022* — [DOI](https://doi.org/10.1609/aaai.v36i8.20845)

### 2021

- A Global DAG Task Scheduler Using Deep Reinforcement Learning and Graph Convolution Network — Hyunsung Lee, Sangwoo Cho, Yeongjae Jang, Jinkyu Lee, Honguk Woo. *IEEE Access 2021* — [DOI](https://doi.org/10.1109/ACCESS.2021.3130407)
- Repot: Transferable Reinforcement Learning for Quality-Centric Networked Monitoring in Various Environments — Youngseok Lee, Woo Kyung Kim, Sung Hyun Choi, Ikjun Yeom, Honguk Woo. *IEEE Access 2021* — [DOI](https://doi.org/10.1109/ACCESS.2021.3125008)
- Efficient User-Level Multi-Path Utilization in RDMA Networks — Sugi Lee, Yusung Kim, Honguk Woo, Ikjun Yeom. *IEEE Access 2021* — [DOI](https://doi.org/10.1109/ACCESS.2021.3110840)
- Differentiable Ranking Metric Using Relaxed Sorting for Top-K Recommendation — Hyunsung Lee, Sangwoo Cho, Yeongjae Jang, Jaekwang Kim, Honguk Woo. *IEEE Access 2021* — [DOI](https://doi.org/10.1109/ACCESS.2021.3105389)
- Gemma: Reinforcement Learning-Based Graph Embedding and Mapping for Virtual Network Applications — Minjae Park, Youngseok Lee, Ikjun Yeom, Honguk Woo. *IEEE Access 2021* — [DOI](https://doi.org/10.1109/ACCESS.2021.3100283)
- ML for RT: Priority Assignment Using Machine Learning — Seunghoon Lee, Hyeongboo Baek, Honguk Woo, Kang G. Shin, Jinkyu Lee. *2021 IEEE 27th Real-Time and Embedded Technology and Applications Symposium (RTAS) 2021* — [DOI](https://doi.org/10.1109/RTAS52030.2021.00018)
- GPU-Ether: GPU-native Packet I/O for GPU Applications on Commodity Ethernet — Changue Jung, Suhwan Kim, Ikjun Yeom, Honguk Woo, Younghoon Kim. *IEEE INFOCOM 2021 - IEEE Conference on Computer Communications 2021* — [DOI](https://doi.org/10.1109/INFOCOM42981.2021.9488699)
- Deep Learning-Based Logging Recommendation Using Merged Code Representation — Suin Lee, Youngseok Lee, Chan-Gun Lee, Honguk Woo. *IT Convergence and Security: ICITCS 2020 2021* — [DOI](https://doi.org/10.1007/978-981-15-9354-3_5)

### 2020

- rocorl: Transferable Reinforcement Learning-Based Robust Control for Cyber-Physical Systems With Limited Data Updates — Gwangpyo Yoo, Minjong Yoo, Ikjun Yeom, Honguk Woo. *IEEE Access 2020* — [DOI](https://doi.org/10.1109/ACCESS.2020.3044945)
- Fixed Priority Global Scheduling from a Deep Learning Perspective — Hyunsung Lee, Michael Wang, Honguk Woo. *arXiv 2020* — [arXiv](https://arxiv.org/abs/2012.03002)
- Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers — Syed Farhan Alam Zaidi, Faraz Malik Awan, Minsoo Lee, Honguk Woo, Chan-Gun Lee. *IEEE Access 2020* — [DOI](https://doi.org/10.1109/ACCESS.2020.3040065)
- Panda: Reinforcement Learning-Based Priority Assignment for Multi-Processor Real-Time Scheduling — Hyunsung Lee, Jinkyu Lee, Ikjun Yeom, Honguk Woo. *IEEE Access 2020* — [DOI](https://doi.org/10.1109/ACCESS.2020.3029040)
- Continual Prediction of Bug-Fix Time Using Deep Learning-Based Activity Stream Embedding — Youngseok Lee, Suin Lee, Chan-Gun Lee, Ikjun Yeom, Honguk Woo. *IEEE Access 2020* — [DOI](https://doi.org/10.1109/ACCESS.2020.2965627)
- Room-Area Adhoc Group Management for Timely Coordination of Voice-Enabled Consumer Devices — Doohwan Song, Jooyoung Park, Honguk Woo. *ICCE 2020* — [DOI](https://doi.org/10.1109/ICCE46568.2020.9043089)

### 2019

- SCARL: Attentive Reinforcement Learning-Based Scheduling in a Multi-Resource Heterogeneous Cluster — Mukoe Cheong, Hyunsung Lee, Ikjun Yeom, Honguk Woo. *IEEE Access 2019* — [DOI](https://doi.org/10.1109/ACCESS.2019.2948150)
- Resource-Efficient Sensor Data Management for Autonomous Systems Using Deep Reinforcement Learning — Seunghwan Jeong, Gwangpyo Yoo, Minjong Yoo, Ikjun Yeom, Honguk Woo. *Sensors 2019* — [DOI](https://doi.org/10.3390/s19204410)
- Event-Triggered Ephemeral Group Communication and Coordination over Sound for Smart Consumer Devices — Doohwan Song, Ikjun Yeom, Honguk Woo. *Sensors 2019* — [DOI](https://doi.org/10.3390/s19081883)
- Deep Reinforcement Learning Based Sensor Data Management for Vehicles — Jeongmin Moon, Mukoe Cheong, Ikjun Yeom, Honguk Woo. *International Conference on Information Networking (ICOIN) 2019* — [DOI](https://doi.org/10.1109/ICOIN.2019.8718108)

## Projects

Source: https://csiagentgroup.com/projects/

- **AI Computing Infrastructure Enhancement (GPU Rental Support)** (completed · 2026.01.01 – 2026.06.30 · Principal Investigator)
  Supporting AI research with GPU computing resources through the MSIT GPU Rental Support User Support Program (RQT-25-120157), including language-model-based skill grounding and embodied-agent research.
  Topics: GPU Rental Support, 인프라 지원, Embodied AI, MSIT, RQT-25-120157
- **Development of Medical Domain-Specific Foundation Models with Acryl** (completed · 2025.05.01 – 2025.11.30 · Principal Investigator)
  Developing foundation models for medical applications through an industry-academic research project with Acryl.
  Topics: Medical AI, Foundation Models, Acryl, 아크릴
- **AI-Based PS-LTE Access Optimization with PolarisAI** (completed · 2024.08.01 – 2024.12.31 · Principal Investigator)
  Researching AI-based methods to improve large-scale PS-LTE terminal access in areas where public safety and railway networks experience radio interference, in collaboration with PolarisAI.
  Topics: PS-LTE, Wireless Networks, PolarisAI, 폴라리스
- **Distributed Learning for Elastic Scaling with Samsung Electronics** (completed · 2023.06.16 – 2024.04.15)
  Developing distributed learning scheduling algorithms and scalable evaluation models for systems of varying sizes, in collaboration with Samsung Electronics.
  Topics: Distributed Learning, Elastic Scaling, GPU Scheduling, Samsung Electronics
- **Elastic GPU Cluster Scheduling and Distributed Learning Management** (completed · 2022.04.01 – 2022.12.31)
  Developing elastic distributed learning management to improve GPU cluster utilization and reduce training time, with cluster monitoring, scaling-overhead optimization, and management agents in collaboration with Samsung Electronics.
  Topics: GPU Clusters, Distributed Learning, Elastic Scheduling, Samsung Electronics
- **Retrieval-Augmented Knowledge Search with LG Electronics** (ongoing · 2026)
  Improving retrieval-augmented knowledge search for research and development documents through document-level context, query decomposition, and knowledge graph integration.
  Topics: Retrieval-Augmented Generation, Knowledge Graph, LG Electronics
- **Reconfigurable Lifelong Learning of VLA Models for Super-adaptive Embodied Agents** (ongoing · 2026.11.20 (4 months) · Principal Investigator)
  Using B200 GPU computing support to study reconfigurable lifelong learning of vision-language-action models for highly adaptive embodied agents, including iterative experience collection, curation, retraining, and rollout evaluation.
  Topics: B200, GPU Computing Support, 인프라 지원, Vision-Language-Action, Lifelong Learning
- **Resource-Intensive AI Technologies Based on Sustainable GPU Integrated Platforms** (ongoing · 2026.04.01 – 2028.12.31 · Sub-project Investigator)
  Integrating distributed university GPU resources into shared computing infrastructure through the IITP computing resource-intensive AI application technology development program. The project develops GPU pooling and GPU-as-a-Service operations, with the group's research focusing on physical AI foundation models and collaboration among heterogeneous robots.
  Topics: GPU Infrastructure, GPU-as-a-Service, Physical AI, Foundation Models, IITP
- **Development of Leading Talent in Medical Domain-Specific Generative AI** (ongoing · 2026.04.01 – 2029.12.31 · Participant)
  Training researchers through industry-academic collaboration on medical generative AI, including adaptive state estimation, vision-language-action skills, and safe physical AI control for medical applications.
  Topics: Generative AI, Medical AI, Vision-Language-Action, Talent Development
- **V2X Operation Optimization Using Deep Reinforcement Learning** (ongoing · 2026.03.30 – 2027.03.29 · Principal Investigator)
  Developing reinforcement learning methods for electric vehicle charging, discharging, and energy-market bidding, with scalable fleet scheduling and robust adaptation to uncertain operating conditions.
  Topics: Reinforcement Learning, V2X, V2G, Hyundai Motor, Kia
- **Reactive Skill Diffusion for Real-world Embodied AGI** (ongoing · 2026.03.01 – 2029.02.28 · Principal Investigator)
  Developing reactive skill diffusion guided by world models, collaborating agents, and memory to support real-world adaptation, heterogeneous robot collaboration, and continual growth of embodied intelligence.
  Topics: Embodied AI, Skill Diffusion, World Models, NRF
- **Autonomous Cluster Management** (ongoing · 2025.12.30 – 2026.10.29 · Principal Investigator)
  Developing a multi-agent framework for GPU cluster fault detection, root cause analysis, and self-healing, combining operational data analysis with the generation and verification of recovery policies.
  Topics: Root Cause Analysis, Multi-Agent Systems, GPU Clusters, Samsung Research
- **Test-Time Storage Scaling for LLM Serving (HiPER Phase 3)** (ongoing · 2026.07.01 – 2029.06.30)
  Investigating test-time storage scaling that combines neural memory and vector storage to improve long-context handling, reasoning, and inference efficiency in large language model serving.
  Topics: LLM Serving, Neural Memory, Vector Storage, Samsung HiPER
- **Adaptive Privacy Compliance with Hybrid Legal AI and Open-Weight Language Models** (completed · 2024.09.01 – 2026.08.31 · Principal Investigator)
  Combining rule-based expert systems and open-weight language models to check privacy requirements, verify compliance checklists, and assist with document corrections.
  Topics: Privacy, Rule-Based AI, sLLM, Jikida, 지키다
- **Artificial Intelligence Graduate School Program(Sungkyunkwan University)** (ongoing · 2019.04.01 – 2028.12.31 · Participant)
  Supporting graduate education and research in artificial intelligence at Sungkyunkwan University and training researchers through AI research and academic activities.
  Topics: Artificial Intelligence, Graduate Education, Talent Development
- **BK21 Education and Research Center for Sustainable Future Computing** (ongoing · 2024.03.01 – 2027.08.31 · Participant)
  Supporting graduate students and research training in software and AI through the laboratory's participation in the BK21 program.
  Topics: BK21, Graduate Education, Talent Development
- **Deep Learning-Based 3D Golf Swing Analysis and Launch Monitor (EXSWING)** (completed · 2020.07.01 – 2021.06.30 · Participant)
  Developing a golf launch monitor that uses deep learning and dual-camera 3D pose estimation to analyze swings, recognize clubs, and provide personalized practice guidance.
  Topics: Deep Learning, 3D Pose Estimation, Sports AI, EXSWING
- **AI Star Fellowship Support Program(Sungkyunkwan Univ.)** (ongoing · 2025.07.01 - 2030.12.31 · Sub-project Investigator)
  Developing synergistic multi-agent technologies for companion AI services, including collaborative planning, interoperability, continual collective learning, and well-care service integration. The lab leads subproject 2 within the Sungkyunkwan University AI Star Fellowship consortium.
  Topics: Multi-Agent Systems, Reinforcement Learning
- **Accelerated Insight Reasoning via Continual Learning** (ongoing · 2025.04.01 - 2029.12.31 · Principal Investigator)
  Developing advanced techniques for policy adaptation in reinforcement learning using cross-domain skill diffusion methods for improved generalization
  Topics: Reinforcement Learning, Transfer Learning, Skill Diffusion
- **Development of Open-Ended Alignment Fluxional AI for Ever-changing Environment and Value** (ongoing · 2024.07.01 - 2031.12.31 · Participating Investigator)
  Contributing to Out-thinking Alignment AI within the Open-Ended Alignment consortium, with research on semantic-skill-based learning, adaptation to changing environments, and replanning for embodied agents.
  Topics: Reinforcement Learning, Embodied AI
- **Self-directed Multi-modal Intelligence for solving unknown, open domain problems** (ongoing · 2022.04.01 - 2026.12.31 · Principal Investigator)
  Securing autonomous learning and adaptation technology for open-domain complex problem situations and demonstrating platform-based agent services
Advancing self-supervised learning, meta few-shot learning, and lifelong reinforcement learning for autonomous AI and developing integrated models
  Topics: Lifelong learning, meta learning
- **Adaptive Personality for Intelligent Agents** (ongoing · 2022.04.01 - 2026.12.31 · Sub-project Investigator)
  Development of AI agent technology that forms personality based on multimodal information of the target, learns according to the interaction partner, and exhibits social behavior
  Topics: Personality, OCEAN
- **Development of a framework to facilitate applications and developments of large-scale AI between a datacenter and an edge NPU based on federated inference/training** (completed · 2021.04.01 – 2024.12.31 · Sub-project Investigator)
  Advancement of federated learning processors between edge and server
Development of federated inference processors between edge and server
Development of edge NPU hardware performance simulator/profiler
Development of distributed deployment algorithms for federated inference models across edge-server NPUs
  Topics: Federated learning
- **Development of Core AI Software for Drones** (completed · 2020.04.23 – 2024.12.31 · Sub-project Investigator)
  Development and continuous improvement of core AI technologies and software for services such as situation understanding, autonomous control, swarm collaboration, and emergency response using large-scale data collected from swarm drones, with public release
  Topics: Drone AI
- **ICT Creative Consilience Program** (ongoing · 2020.07.01 – 2029.12.31 · Participant)
  Cultivating innovative leader-type professional researchers to solve future societal problems and lead new technologies based on ICT technology and multidisciplinary knowledge
  Topics: ICT Research
- **Adaptive Federated Learning in Dynamic Heterogeneous Environment** (completed · 2021.04.01 – 2022.12.31 · Sub-project Investigator)
  Development of adaptive federated learning technology that is robust to statistical heterogeneity of data and system heterogeneity of devices in dynamic device and data environments, while optimally reflecting the characteristics of individual devices and users as well as application requirements
  Topics: Federated learning, Dynamic Device Environments
- **Real-Time Data Management and Adaptive Model Serving for Autonomous Systems** (completed · 2018.11.01 – 2020.10.31 · Principal Investigator)
  An adaptive model serving architecture based on real-time data management that executes appropriate machine learning models and makes decisions without delay under limited resource conditions to proactively respond to changes in the physical operating environment of automated systems
  Topics: Automated Systems
- **Development of a Personal Online Golf Simulator (EXTRACE) Based on GIS Information and AI Technology** (completed · 2021.09.01 – 2023.08.31 · Sub-project Investigator)
  Development of a personal golf simulator
Securing technology for the development of a personal golf launch monitor with expert-level measurement accuracy
  Topics: GIS Information
- **Policy Generalization via Multimodal Skill Transfer** (completed · 2023.03.01 – 2026.02.28 · Principal Investigator)
  Targeting real-world environments (dynamic environments and complex multitasks) where Embodied AI agents operate, we aim to achieve a high level of policy generalization for agents capable of quickly learning and adapting problem-solving methods for new tasks (unseen tasks) and unexplored, dynamic environmental conditions (unexplored, dynamic environments)
  Topics: Embodied AI, dynamic environments
- **HiPER (High-Performance Exabyte stoRage)** (completed · 2024.05.16 – 2026.05.15)
  Focusing on large-scale AI workloads, we aim to develop a host software stack optimized for storage access patterns, design a storage architecture tailored to these patterns, and further optimize the integrated host software stack for efficient Peta-scale data processing.
  Topics: Multimodal LLM, Retrieval-Augmented Generation
- **Research on Storage Systems and Application Framework Optimization for Next-Generation Computing Environments** (completed · 2019.08.01 – 2022.07.31)
  Research on data-centric computing environments leveraging SmartSSDs extended with CPUs, FPGAs, and GPUs, focusing on system software optimization for data center-scale storage systems based on NVMe-oF, as well as application-level optimization for DBMS and distributed key-value systems utilizing next-generation SSDs.
  Topics: FPGA Acceleration, Storage System Optimization
- **Detection Method for Factors Influencing AI Agent Quality** (completed · 2022.05.16 – 2022.12.16)
  Research on methods to analyze and improve the decision-making quality of AI agents by identifying influential policy factors, diagnosing service errors, and supporting effective policy network debugging in complex environments.
  Topics: AI Agent
- **Development of an Open-Source LLM-Based Knowledge Graph Generation Pipeline** (completed · 2023.09.01 – 2023.11.30)
  Design and implementation of a pipeline to automate knowledge graph generation using LLMs, focusing on prompt design and application testing for tasks such as NER and RE. The project includes benchmarking open-source LLMs, dataset selection, text preprocessing, prompt engineering, and evaluation of the generated knowledge graphs.
  Topics: Knowledge Graph

## News

Source: https://csiagentgroup.com/

- **2026-09-25 — Four Papers Accepted to NeurIPS 2026 (1 Oral, 1 Spotlight)**
  Our CSI-Agent Group @ SKKU had four papers accepted to the NeurIPS 2026 Main Track, including one Oral (0.36% of submissions), one Spotlight (0.95% of submissions), and two Poster presentations.
- **2026-08-20 — Three Papers Accepted to EMNLP 2026 Main Conference and One to CIKM 2026**
  Our CSI-Agent Group @ SKKU had three papers accepted to the EMNLP 2026 Main Conference and one paper accepted to CIKM 2026.
- **2026-06-18 — Two Papers Accepted to IROS and ECCV 2026**
  Our CSI-Agent Group @ SKKU had papers accepted to IROS 2026 and ECCV 2026.
- **2026-05-15 — Three Papers Accepted to ICML 2026**
  Our CSI-Agent Group @ SKKU had 3 papers accepted to ICML 2026.
- **2025-09-19 — Three Papers Accepted to NeurIPS 2025 (2 Spotlight)**
  Our CSI-Agent Group @ SKKU had 3 papers on embodied & physical AI accepted to NeurIPS 2025, including 2 Spotlight papers.
- **2025-01-10 — Four Papers Accepted to ICLR, ICML, and AAAI 2025**
  Our CSI-Agent Group @ SKKU had 4 papers accepted to ICLR, ICML, and AAAI 2025.