Publications

* Equal contribution

Preprints Conferences Journals Workshops

Preprints

  1. Preprint
    Do VLAs Really Follow Instructions? Diagnosing How-Level Instruction Following in Vision-Language-Action Models
    Sangwu Park, Wonjoong Kim, Yeonjun In, and Chanyoung Park
    arXiv
  2. Preprint
    ManiPhysicsBench: Physics-Based Assessment of Object Preservation in VLA Manipulation
    Sangwu Park, Yeonjun In, Wonjoong Kim, Sungwon Kim, Sein Kim, and Chanyoung Park
    arXiv
  3. Preprint
    ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
    Sungho Park, Wonjoong Kim, Jue Zhang, Wook-Shin Han, Pengfei Gao, Chanyoung Park, Yongqiang Yao, Rao Fu, Elsie Nallipogu, Qingwei Lin, and Victor Rühle
    arXiv
  4. Preprint
    Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
    Yeonjun In, Mehrab Tanjim, Jayakumar Subramanian, Sungchul Kim, Uttaran Bhattacharya, Wonjoong Kim, Sangwu Park, Somdeb Sarkhel, and Chanyoung Park
    arXiv

Conferences

  1. NeurIPS
    AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
    Sungho Park, Wonjoong Kim, Rongyuan Tan, Jue Zhang, Wook-Shin Han, Pengfei Gao, Chanyoung Park, Yongqiang Yao, Rao Fu, Elsie Nallipogu, Qingwei Lin, Saravan Rajmohan, and Dongmei Zhang
    In Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  2. NeurIPS
    PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
    Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, and Chanyoung Park
    In Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  3. NeurIPS
    Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
    Yeonjun In, Wonjoong Kim, Sangwu Park, Kanghoon Yoon, and Chanyoung Park
    In Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  4. NeurIPS
    Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
    Sein Kim, Sangwu Park, Hongseok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, and Chanyoung Park
    In Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  5. ECCV
    Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
    Jiwan Kim, Kibum Kim, Wonjoong Kim, Byung-Kwan Lee, and Chanyoung Park
    In European Conference on Computer Vision (ECCV), 2026
    arXiv
  6. ICML
    Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
    Wonjoong Kim, Sangwu Park, Yeonjun In, Sein Kim, Dongha Lee, and Chanyoung Park
    In International Conference on Machine Learning (ICML), 2026
    arXiv
  7. ACL
    Reasoning Structure Matters for Safety Alignment of Reasoning Models
    Yeonjun In, Wonjoong Kim, Sangwu Park, and Chanyoung Park
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
    arXiv
  8. EMNLP Findings
    Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
    Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, and Chanyoung Park
    In Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    arXiv
  9. SIGIR
    Dynamic Time-aware Continual User Representation Learning
    Seungyoon Choi, Sein Kim, Hongseok Kang, Wonjoong Kim, and Chanyoung Park
    In ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2025
    arXiv
  10. NAACL Findings
    SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials
    Wonjoong Kim*, Sangwu Park*, Yeonjun In, Seokwon Han, and Chanyoung Park
    In Findings of the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), 2025
    arXiv
  11. WWW
    DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
    Seungyoon Choi*, Wonjoong Kim*, Sungwon Kim, Yeonjun In, Sein Kim, and Chanyoung Park
    In The Web Conference (WWW), 2024
    Oral Presentation
    arXiv
  12. KDD
    Task-Equivariant Graph Few-shot Learning
    Sungwon Kim, Junseok Lee, Namkyeong Lee, Wonjoong Kim, Seungyoon Choi, and Chanyoung Park
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
    arXiv
  13. ICONIP
    An improved time-series forecasting model using time series decomposition and gru architecture
    Hyunjae Jo*, Wonjoong Kim*, Hyokyung Goh*, and Chihyuck Jun
    In International Conference on Neural Information Processing (ICONIP), 2021
    DOI

Journals

  1. Complexity
    Forecasting CDS term structure based on nelson–siegel model and machine learning
    Wonjoong Kim, Gunho Jung, and Sunyong Choi
    Complexity (SCIE), 2020
    DOI

Workshops

  1. KDD
    Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
    Wonjoong Kim, Sangwu Park, Yeonjun In, Sein Kim, Dongha Lee, and Chanyoung Park
    In KDD Workshop on Evaluation and Trustworthiness of Agentic AI, 2026
    arXiv
  2. KDD
    Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
    Jiwan Kim, Kibum Kim, Wonjoong Kim, Byung-Kwan Lee, and Chanyoung Park
    In KDD Workshop on Resource-Efficient Learning for Knowledge Discovery, 2026
    Oral Presentation
    arXiv
  3. KDD
    Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
    Yeonjun In, Wonjoong Kim, Sangwu Park, Kanghoon Yoon, and Chanyoung Park
    In KDD Workshop on Personal Intelligence in Agentic AI Era, 2026
    Best Paper Award
    arXiv
  4. ICML
    Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
    Yeonjun In, Mehrab Tanjim, Jayakumar Subramanian, Sungchul Kim, Uttaran Bhattacharya, Wonjoong Kim, Sangwu Park, Somdeb Sarkhel, and Chanyoung Park
    In ICML Workshop on Failure Modes of Agentic AI, 2026
    Also presented at the KDD 2026 Workshop on Agentic Software Engineering (Oral)
    arXiv
  5. ICML
    Test-Time Training for Visual Foresight Vision-Language-Action Models
    Sangwu Park, Wonjoong Kim, Yeonjun In, Sein Kim, Hongseok Kang, and Chanyoung Park
    In ICML Workshop on Continual Adaptation at Scale: Towards Sustainable AI, 2026
    arXiv
  6. ICLR
    Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
    Sein Kim, Sangwu Park, Hongseok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, and Chanyoung Park
    In ICLR Workshop on AI with Recursive Self-Improvement, 2026
    Also presented at the KDD 2026 Workshop on Agentic Software Engineering (Oral)
    arXiv
  7. NeurIPS
    Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
    Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, and Chanyoung Park
    In NeurIPS Workshop of Reliable ML from Unreliable Data, 2025
    arXiv