이서영

1. [6]
   Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation
   In-Chang Baek^*, Seo-Young Lee^*, Sung-Hyun Kim, Geumhwan Hwang, Kyung-Joong Kim
   IEEE Transactions on Games (Early Access) (2026) · 게재됨

   arXiv DOI 코드
2. [5]
   Shared Representation for 3D Pose Estimation, Action Classification, and Progress Prediction from Tactile Signals
   Isaac Han, Seoyoung Lee, Sangyeon Park, Ecehan Akan, Yiyue Luo, Jeffrey DelPreto, Kyung-Joong Kim
   arXiv (2026) · 프리프린트

   DOI
3. [4]
   Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation Reinforcement Learning
   Sung-Hyun Kim, Geum-Hwan Hwang, In-Chang Baek, Seo-Young Lee, Kyung-Joong Kim
   IEEE Conference on Games (CoG 2026) (2026) · 채택됨

   최우수논문상 후보

   arXiv 학회
4. [3]
   IPCGRL: Language-Instructed RL for Procedural Level Generation
   In-Chang Baek, Sung-Hyun Kim, Seo-Young Lee, Dong-Hyeon Kim, Kyung-Joong Kim
   IEEE Conference on Games (CoG 2025) (2025) · 게재됨

   DOI 코드
5. [2]
   Automatic Curriculum Design for Zero-Shot Human-AI Coordination
   Won-Sang You, Tae-Gwan Ha, Seo-Young Lee, Kyung-Joong Kim
   IEEE Access (2025) · 게재됨

   DOI
6. [1]
   Smart Insole: Predicting 3D Human Pose from Foot Pressure
   Isaac Han, Seoyoung Lee, Sangyeon Park, Ecehan Akan, Yiyue Luo, Kyung-Joong Kim
   2nd NeurIPS Workshop on Touch Processing: From Data to Knowledge, 2024 (2024) · 게재됨

Arcana Trigger

카드 게임 기획·카드 전투·층별 레벨 PCG·통합 개발 · 2인 팀 · 2026.07–08 · 약 2주

NHN Game × AI Hackathon 예선 출품을 위해 2인 팀에서 약 2주간 Unity 6/C# 하이브리드 덱빌딩·탄막 액션 게임을 공동 기획·개발했습니다. 카드 게임 기획, 카드 전투, 매 층의 전체 레벨을 랜덤 생성하는 PCG와 관련 통합을 담당했습니다. 예선을 통과하지 못했으며, 실제 게임 구현과 통합 경험에 초점을 둡니다.