🥈 Excellence Award (우수상)

• Soccer Lineup Optimization based on Spatial Action Values (공간적 행동 가치 기반 축구 라인업 최적화) — Song-Yun Jeong (정송윤), Geonhee Jo (조건희)
• Learning Cooperative Multi-Agent Actions via Semantic Embedding of LLM Natural-Language Instructions (LLM 자연어 지시의 의미 임베딩을 통한 다중 에이전트 협력 행동 학습) — Junhyeok Eom (엄준혁), Hyunwoo Park (박현우)

🥉 Encouragement Award (장려상)

• Phase-aware Online Change-point Detection of Soccer Formations (경기 국면을 고려한 온라인 축구 포메이션 변화점 탐지) — Hyeokje Jo (조혁제), Miru Hong (홍미루)

This comes on top of the six papers accepted at KCC 2026, where Miru Hong also received an Outstanding Paper Award (우수논문상).

Congratulations to all of our students on this wonderful result! 🎉

🏆 Most notably, Miru Hong (홍미루) received an Outstanding Paper Award (우수논문상) for his lead-authored work on soccer cross outcome prediction. Huge congratulations! 🎉

The accepted papers span our work in sports data analytics, spiking neural networks, and multi-agent reinforcement learning:

• Soccer Cross Outcome Prediction with 3D Ball Trajectories and Contextual Information (공의 3차원 궤적과 경기 맥락 정보를 고려한 축구 크로스 결과 예측) — Miru Hong, Minho Lee, Sang-Ki Ko (🏆 Outstanding Paper Award)
• Phase-aware Online Change-point Detection of Soccer Formations (경기 국면을 고려한 온라인 축구 포메이션 변화점 탐지) — Hyeokje Jo, Miru Hong, Sang-Ki Ko
• Soccer Lineup Optimization based on Spatial Action Values (공간적 행동 가치 기반 축구 라인업 최적화) — Song-Yun Jeong, Geonhee Jo, Sang-Ki Ko
• LD-RNN: Recurrent Networks with Learnable Axonal Delays (LD-RNN: 학습 가능한 축삭 지연을 활용한 순환 신경망) — Jeongmin Hong, Hyunwoo Park, Baekryun Seong, Sang-Ki Ko
• Class-wise Dynamic Neuron Group for Power Efficiency (전력 효율성을 위한 클래스별 뉴런 동적 재구성) — Wonmo Lee, Baekryun Seong, Sang-Ki Ko
• Learning Cooperative Multi-Agent Actions via Semantic Embedding of LLM Natural-Language Instructions (LLM 자연어 지시의 의미 임베딩을 통한 다중 에이전트 협력 행동 학습) — Junhyeok Eom, Hyunwoo Park, Sang-Ki Ko

Congratulations to all the students and co-authors on this great collective achievement! 🎉

Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football Miru Hong, Minho Lee, Geonhee Jo, Hyeokje Cho, Hyunsung Kim, Pascal Bauer, and Sang-Ki Ko

The paper introduces ScoutGPT, a generative model that treats football match events as sequential tokens within a language modeling framework. Built on a NanoGPT-based Transformer trained on next-token prediction, ScoutGPT simulates event sequences under hypothetical lineups and uses Monte Carlo sampling to enable counterfactual transfer simulation, capturing player-specific impact beyond traditional static metrics.

Huge congratulations to Miru Hong for leading this work, and to all the co-authors on this great achievement! 🎉

ReSyn: A Generalized Recursive Regular Expression Synthesis Framework Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim, Yo-Sub Han, and Sang-Ki Ko

Huge congratulations to Seongmin Kim for leading this work — your dedication and hard work have truly paid off! Congratulations also to all the co-authors on this great achievement. 🎉

• Hyeokje Cho (조혁제), Department of AI
  • Research area: football data analytics, formation analysis
• Song-Yun Jeong (정송윤), Department of Geoinformatics
  • Research area: football data analytics, player/team performance analysis/optimization
• Jeongmin Hong (홍정민), Department of AI
  • Research area: formal verification of spiking neural networks

Valuing La Pausa: Quantifying Optimal Pass Timing Beyond Speed Minho Lee, Geonhee Jo, Miru Hong, Pascal Bauer, and Sang-Ki Ko

Congratulations to all the authors!

• Multi-modal recommender system using text-to-image generative models and adaptive learning, Expert Systems with Applications, Volume 296, 129086, 2026

• EnCur: Curriculum-based in-context learning with structural encoding for code time complexity prediction, Expert Systems with Applications, Volume 296, 129094, 2026

Congratulations to all the authors!

• Programming Languages (프로그래밍 언어)
• Reliable and Trustworthy AI (신뢰할수있는인공지능)

Please refer to the Teaching page for more details.

Prestigious Conference Papers:

• CodeComplex: Dataset for Worst-Case Time Complexity Prediction at EMNLP 2025 (Findings of EMNLP, BK21 Top Conference)
• Imputing Multi-Agent Trajectories from Event and Snapshot Data in Soccer at CIKM 2025 (BK21 Top Conference)
• Contextual Evaluation of Individual Contributions from Pressing Situations in Football at MLSA 2025

Industry Partnership:

• Capturing Player Impact from Team Action Sequences - A GPT-Based Framework for Transfer Fit published at Hudl Performance Insights 2025

These works represent achievements across our core research areas: programming language understanding, neural network verification, and sports data analytics. Congratulations to all contributors!

Master’s Students:

• Baekryun Seong (성백륜), Department of AI
  • Research area: spiking neural network, formal verification, reinforcement learning
• Jaewon Kim (김재원), Department of AI
  • Research area: 3D simulation, digital twin

Undergraduate Research Students:

• Junhyeok Eom (엄준혁), Department of AI
  • Research area: multi-agent reinforcement learning

We are excited to have you join our team and look forward to collaborative research and learning!