publications

(*) denotes equal contribution

2026

  1. NeurIPS
    Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs
    Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, and Hyunwoo J Kim
    In Conference on Neural Information Processing Systems (NeurIPS 2026)
    PDF
  2. ECCV
    Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization
    Byungoh Ko, Jinyoung Park, Jongha Kim, Jeehye Na, Jaewon Cho, and Hyunwoo J Kim
    In European Conference on Computer Vision (ECCV 2026)
    PDF
  3. ECCV
    VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
    Seohyun Lee*, Seoung Choi*, Dohwan Ko*, Jongha Kim, and Hyunwoo J Kim
    In European Conference on Computer Vision (ECCV 2026)
    PDF
  4. CVPR
    DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
    Joonmyung Choi, Sanghyeok Lee, Jongha Kim, Sehyung Kim, Dohwan Ko, Jihyung Kil, and Hyunwoo J Kim
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)
    PDF
  5. WACV
    Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering
    Jongha Kim, Byungoh Ko, Jeehye Na, Jinsung Yoon, and Hyunwoo J Kim
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026)
    PDF
  6. AAAI
    TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
    Jongha Kim, Minseong Bae, Sanghyeok Lee, Jinsung Yoon, and Hyunwoo J Kim
    In AAAI Conference on Artificial Intelligence (AAAI 2026)
    PDF
  7. InfoScience
    Improved Query Specialization for Transformer-based Visual Relationship Detection
    Jongha Kim, Jihwan Park, Jinyoung Park, Jinyoung Kim, Sehyung Kim, and Hyunwoo J Kim
    Information Sciences
    PDF
  8. Under Review
    MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
    Seohyun Lee*, Jongha Kim*, Dohwan Ko, Ji Soo Lee, Seoung Choi, Jayun Ku, and Hyunwoo J Kim
    In Under Review
    PDF
  9. Under Review
    SuperClip Pyramid for Video Temporal Grounding
    Sanghyeok Lee, Juyeon Ko, Joonmyung Choi, Jongha Kim, Dohwan Ko, Ji Soo Lee, and Hyunwoo J Kim
    In Under Review
    PDF
  10. Under Review
    CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
    Jongha Kim*, Seohyun Lee*, Jonathan Minho Chung, Jinsung Yoon, and Hyunwoo J Kim
    In Under Review
    PDF

2025

  1. AAAI
    VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
    Ji Soo Lee*, Jongha Kim*, Jeehye Na, Jinyoung Park, and Hyunwoo J Kim
    In AAAI Conference on Artificial Intelligence (AAAI 2025)
    PDF Code

2024

  1. CVPR
    Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
    Jongha Kim*, Jihwan Park*, Jinyoung Park*, Jinyoung Kim, Sehyung Kim, and Hyunwoo J Kim
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)
    PDF Code

2023

  1. MICCAI Workshop
    Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification
    Injae Kim*, Jongha Kim*, Joonmyung Choi, and Hyunwoo J Kim
    In MedAGI Workshop at International Conference on Medical Image Computing and Computer-Assisted Intervention (MedAGI@MICCAI 2023)
    Oral Presentation
    PDF

2022

  1. ECCV Workshop
    Object Detection in Aerial Images with Uncertainty-Aware Graph Network
    Jongha Kim, Jinheon Baek, and Sung Ju Hwang
    In European Conference on Computer Vision (ECCV 2022 Workshop)
    PDF