Publications

Preprints

ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models
Dohwan Ko*, Sihyeon Kim*, Yumin Suh, Vijay Kumar, Minseo Yoon, Manmohan Chandraker, Hyunwoo J. Kim

arXiv 2025

@article{ko2025st,
        title={ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models},
        author={Ko, Dohwan and Kim, Sihyeon and Suh, Yumin and Yoon, Minseo and Chandraker, Manmohan and Kim, Hyunwoo J and others},
        year={2025}}

International Conference Publications

LLaMo: Large Language Model-based Molecular Graph Assistant
Jinyoung Park, Minseong Bae, Dohwan Ko, Hyunwoo J. Kim

NeurIPS 2024

@inproceedings{park2024llamo,
        title={LLaMo: Large Language Model-based Molecular Graph Assistant},
        author={Park, Jinyoung and Bae, Minseong and Ko, Dohwan and Kim, Hyunwoo J},
        booktitle={NeurIPS},
        year={2024}}

Large Language Models are Temporal and Causal Reasoners for Video Question Answering
Dohwan Ko*, Ji Soo Lee*, Wooyoung Kang, Byungseok Roh, Hyunwoo J. Kim

EMNLP 2023 Main

@inproceedings{ko2023large,
        title={Large Language Models are Temporal and Causal Reasoners for Video Question Answering},
        author={Dohwan Ko and Ji Soo Lee and Wooyoung Kang and Byungseok Roh and Hyunwoo J. Kim},
        booktitle={EMNLP},
        year={2023}}

Open-Vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Dohwan Ko, Ji Soo Lee, Miso Choi, Jaewon Chu, Jihwan Park, Hyunwoo J. Kim

ICCV 2023

@inproceedings{ko2023open,
        title={Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models},
        author={Ko, Dohwan and Lee, Ji Soo and Choi, Miso and Chu, Jaewon and Park, Jihwan and Kim, Hyunwoo J},
        booktitle={ICCV},
        year={2023}}

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Dohwan Ko*, Joonmyung Choi*, Hyeong Kyu Choi, Kyoung-Woon On, Byungseok Roh, Hyunwoo J. Kim

CVPR 2023

@inproceedings{ko2023melrt,
        title={MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models},
        author={Ko, Dohwan and Choi, Joonmyung and Choi, Hyeong Kyu and On, Kyoung-Woon and Roh, Byungseok and Kim, Hyunwoo J},
        booktitle={CVPR},
        year={2023}}

Video-Text Representation Learning via Differentiable Weak Temporal Alignment
Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim

CVPR 2022

@inproceedings{ko2022video,
        title={Video-Text Representation Learning via Differentiable Weak Temporal Alignment},
        author={Ko, Dohwan and Choi, Joonmyung and Ko, Juyeon and Noh, Shinyeong and On, Kyoung-Woon and Kim, Eun-Sol and Kim, Hyunwoo J},
        booktitle={CVPR},
        year={2022}}

International Journal Publications

Randomly Shuffled Convolution for Self-Supervised Representation Learning
Youngjin Oh*, Minkyu Jeon*, Dohwan Ko, Hyunwoo J. Kim

Information Sciences 2023

@article{oh2023randomly,
        title={Randomly shuffled convolution for self-supervised representation learning},
        author={Oh, Youngjin and Jeon, Minkyu and Ko, Dohwan and Kim, Hyunwoo J},
        journal={Information Sciences},
        year={2023}}

Search-and-Attack: Temporally SparseAdversarial Perturbations on Videos
Hwan Heo*, Dohwan Ko*, Jaewon Lee*, Youngjoon Hong, Hyunwoo J. Kim

IEEE Access 2021

@article{heo2021search,
        title={Search-and-attack: temporally sparse adversarial perturbations on videos},
        author={Heo, Hwan and Ko, Dohwan and Lee, Jaewon and Hong, Youngjoon and Kim, Hyunwoo J},
        journal={IEEE Access},
        year={2021}}