CV

The latest PDF version is available here: Download CV.

Research Interests

Dense prediction for real-world vision systems, object detection, human-object interaction detection, efficient and transferable training, vision-language-action models, and embodied AI.

Appointment

• Postdoctoral Researcher, KAIST
  March 2026 - Present
  Daejeon, South Korea
  Supervised by Hyunwoo J. Kim

• Research Assistant, Korea University
  September 2022 - June 2023
  Seoul, South Korea

• Research Intern, Kakao Brain
  December 2021 - June 2022
  Pangyo, South Korea
  Supervised by Byungseok Roh

Education

• Ph.D. student in Computer Science, Korea University
  March 2021 - February 2026
  Supervised by Prof. Hyunwoo J. Kim

• Bachelor’s degree in Computer Science, Korea University
  March 2017 - February 2021

Publications

RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection Permalink Code

Jihwan Park, Chanhyeong Yang, Jinyoung Park, Taehoon Song, Hyunwoo J. Kim
Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning Permalink

Kyujin Lee, Injae Kim, Jihwan Park, Yejun Ju, Minseok Joo, Hyunwoo J. Kim
arXiv, 2026

Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization Permalink Code

Jihwan Park, Taehoon Song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim
AAAI Conference on Artificial Intelligence (AAAI), Oral, 2026

Improved Query Specialization for Transformer-based Visual Relationship Detection Permalink Code

Jongha Kim, Jihwan Park, Jinyoung Park, Jinyoung Kim, Sehyung Kim, Hyunwoo J. Kim
Information Sciences, 2026

Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection Permalink Code

Chanhyeong Yang, Taehoon Song, Jihwan Park, Hyunwoo J. Kim
Advances in Neural Information Processing Systems (NeurIPS), 2025

Super-class Guided Transformer for Zero-Shot Attribute Classification Permalink Code

Sehyung Kim*, Chanhyeong Yang*, Jihwan Park, Taehoon Song, Hyunwoo J. Kim
AAAI Conference on Artificial Intelligence (AAAI), 2025

Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble Permalink Code

Juhan Cha*, Minseok Joo*, Jihwan Park, Sanghyeok Lee, Injae Kim, Hyunwoo J. Kim
arXiv, 2024

Groupwise Query Specialization and Quality-aware Multi-assignment for Transformer-based Visual Relationship Detection Permalink Code

Jongha Kim*, Jihwan Park*, Jinyoung Park*, Jinyoung Kim, Sehyung Kim, Hyunwoo J. Kim
Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models Permalink Code

Dohwan Ko, Ji Soo Lee, Miso Choi, Jaewon Chu, Jihwan Park, Hyunwoo J. Kim
International Conference on Computer Vision (ICCV), 2023

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection Permalink Code

Jihwan Park, SeungJun Lee, Hwan Heo, Hyeong Kyu Choi, Hyunwoo J. Kim
Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Deformable Graph Convolutional Networks Permalink Code

Jinyoung Park, Sungdong Yoo, Jihwan Park, Hyunwoo J. Kim
AAAI Conference on Artificial Intelligence (AAAI), 2022

Professional Services

• Reviewer, The British Machine Vision Conference (BMVC), 2026
• Reviewer, European Conference on Computer Vision (ECCV), 2026
• Reviewer, AAAI Conference on Artificial Intelligence (AAAI), 2025, 2026, 2027
• Reviewer, Conference on Neural Information Processing Systems (NeurIPS), 2026
• Reviewer, Conference on Computer Vision and Pattern Recognition (CVPR), 2024, 2025, 2026

Tutorials

• KCCV 2023 Tutorial - Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
• KCCV 2022 Tutorial - End-to-End Human-Object Interaction Detection with Transformers