|
I aim to build a J.A.R.V.I.S.-like Proactive AI assistant that integrates visual cues such as gaze and individual user personas, while autonomously identifying and continually developing proactive assistance skills. My research includes:
Proactive AIProactive Assistance, Intervention Timing, Personalized Guidance
Self-Evolving AIPlanner Evolution, Planner–Policy Co-evolution, Continual Learning, Learning from Feedback
Video UnderstandingVideo Temporal Grounding, Fine-grained Video Understanding, Streaming Video Understanding, Hierarchical Procedural Understanding
Self-supervised LearningRepresentation Learning, Contrastive Learning
Data-efficient LearningSemi-supervised Learning, Weakly Supervised Learning, Domain Generalization, Learning with Noisy Labels
|
News
[2026.10] (New!) Preprint: Improving Proactive AI Assistance with Hierarchical Procedural Understanding.
[2026.10] (New!) Visiting Researcher at New York University (NYU) (Oct. 2026–Dec. 2026)
(Mentor:
Prof. Mengye Ren
)
[2026.08] One paper accepted to EMNLP 2026 Findings.
[2026.06] Our CVPR 2026 paper received the Compute Gold Star (0.4%), a distinguished recognition for transparent compute reporting and outstanding research contribution.
[2026.04] One paper accepted to ACL 2026 Findings.
[2026.02] One paper accepted to CVPR 2026.
[2025.12] Visiting Researcher at Nanyang Technological University (NTU) (Dec. 2025–Feb. 2026)
(Mentors:
Prof. Boyang Albert Li
and
Prof. Jaehong Yoon
)
[2025.11] One paper got accepted to AAAI 2026.
[2025.08] I received a Ph.D fellowship from NRF (National Research Foundation) of Korea.
[2025.07] Two papers got accepted to BMVC 2025.
[2025.05] One paper got accepted to ACL 2025.
[2024.12] One paper got accepted to AAAI 2025.
[2024.10] One paper got accepted to WACV 2025.
[2024.07] Two papers got accepted to ECCV 2024.
[2024.02] One paper got accepted to CVPR 2024.
[2024.01] One paper got accepted to EAAI 2024.
|
Preprints(*: equal contribution, ‡: corresponding author) |
|
[P2] Improving Proactive AI Assistance with Hierarchical Procedural Understanding
Jin-Seop Lee, TaeYeon Won, SeongJun Jung, JungHoon Kim, Boyang Albert Li, Jin-Young Park, Jaehong Yoon‡, Jee-Hyong Lee‡
Preprint
@misc{proactive,
title = {Improving Proactive AI Assistance with Hierarchical Procedural Understanding},
author = {Lee, Jin-Seop and Won, TaeYeon and Jung, SeongJun and Kim, JungHoon and Li, Boyang Albert and Park, Jin-Young and Yoon, Jaehong and Lee, Jee-Hyong},
year = {2026},
note = {Preprint},
url = {https://jinsuby.github.io/data/ProactiveCoach.pdf}
}
|
|
|
[P1] CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation
Joohyeon Lee*, Jin-Seop Lee*, Jee-Hyong Lee‡
Preprint
@misc{count,
title = {CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation},
author = {Lee, Joohyeon and Lee, Jin-Seop and Lee, Jee-Hyong},
year = {2025},
eprint = {2508.10710},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
doi = {10.48550/arXiv.2508.10710},
url = {https://arxiv.org/abs/2508.10710}
}
arXiv 2508.10710
|
Publications(*: equal contribution, ‡: corresponding author) |
2026 |
|
|
[C12] InterventionBench: Can LLM Agents Adapt to Mid-task User Interventions?
Jaehoon Lee, Suyoung Bae, Jin-Seop Lee, YunSeok Choi‡, Jee-Hyong Lee‡
EMNLP 2026 Findings
@inproceedings{intervention,
title = {InterventionBench: Can LLM Agents Adapt to Mid-task User Interventions?},
author = {Lee, Jaehoon and Bae, Suyoung and Lee, Jin-Seop and Choi, YunSeok and Lee, Jee-Hyong},
year = {2026},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
note = {Accepted for publication},
url = {https://jinsuby.github.io/}
}
|
|
|
[C11] EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL
Jaehoon Lee, CheolWon Na, Suyoung Bae, Jin-Seop Lee, Jihyung Lee, YunSeok Choi‡, Jee-Hyong Lee‡
ACL 2026 Findings
@inproceedings{lee-etal-2026-expo,
title = "{EXPO}-{SQL}: Execution-based Clause-level Policy Optimization for Text-to-{SQL}",
author = "Lee, Jaehoon and
Na, CheolWon and
Bae, Suyoung and
Lee, Jin-Seop and
Lee, Jihyung and
Choi, YunSeok and
Lee, Jee-Hyong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1107/",
doi = "10.18653/v1/2026.findings-acl.1107",
pages = "22000--22019",
ISBN = "979-8-89176-395-1"
}
arXiv 2606.23693
|
|
|
[C10] Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding
Jin-Seop Lee*, SungJoon Lee*, SeongJun Jung, Boyang Li, Jee-Hyong Lee‡
CVPR 2026 (Compute Gold Star, 0.4%)
@InProceedings{refuse,
author = {Lee, Jin-Seop and Lee, SungJoon and Jung, SeongJun and Li, Boyang and Lee, Jee-Hyong},
title = {Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2026},
pages = {10397-10407}
}
arXiv 2511.23151
|
|
|
[C9] BD-Net: Has depth-wise convolution ever been applied in Binary Neural Networks?
DoYoung Kim, Jin-Seop Lee, Noo-ri Kim, SungJoon Lee, Jee-Hyong Lee‡
AAAI 2026
@article{bd,
title = {BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?},
author = {Kim, DoYoung and Lee, Jin-Seop and Kim, Noo-ri and Lee, SungJoon and Lee, Jee-Hyong},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {27},
pages = {22563--22572},
doi = {10.1609/aaai.v40i27.39416},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/39416}
}
arXiv 2511.17633
|
2025 |
|
|
[C8] TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding
Jin-Seop Lee*, Sungjoon Lee*, Jaehan Ahn, Yunseok Choi, Jee-Hyong Lee‡
BMVC 2025
@inproceedings{tag,
author = {Jin-Seop Lee and SungJoon Lee and Jaehan Ahn and YunSeok Choi and Jee-Hyong Lee},
title = {TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year = {2025},
url = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_786/paper.pdf}
}
arXiv 2508.07925
|
|
|
[C7] Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Prediction
Byung-Joon Lee, Jin-Seop Lee, Jee-Hyong Lee‡
BMVC 2025
@inproceedings{stabilizing,
author = {Byung-Joon Lee and Jin-Seop Lee and Jee-Hyong Lee},
title = {Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Prediction},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year = {2025},
url = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1071/paper.pdf}
}
arXiv 2508.18751
|
|
|
[C6] DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph
Jihyung Lee*, Jin-Seop Lee*, Jaehoon Lee, YunSeok Choi‡, Jee-Hyong Lee‡
ACL 2025
@inproceedings{lee-etal-2025-dcg,
title = "{DCG}-{SQL}: Enhancing In-Context Learning for Text-to-{SQL} with Deep Contextual Schema Link Graph",
author = "Lee, Jihyung and
Lee, Jin-Seop and
Lee, Jaehoon and
Choi, YunSeok and
Lee, Jee-Hyong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.748/",
doi = "10.18653/v1/2025.acl-long.748",
pages = "15397--15412",
ISBN = "979-8-89176-251-0"
}
arXiv 2505.19956
|
|
|
[C5] DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization
Jin-Seop Lee, Noo-ri Kim, Jee-Hyong Lee‡
AAAI 2025
@article{domclp,
title = {DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization},
author = {Lee, Jin-Seop and Kim, Noo-ri and Lee, Jee-Hyong},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {17},
pages = {18119--18127},
doi = {10.1609/aaai.v39i17.33993},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/33993}
}
arXiv 2412.09074
|
|
|
[C4] Feature-level and Spatial-level Activation Expansion for Weakly-Supervised Semantic Segmentation
Junsu Choi*, Jin-Seop Lee*, Noo-ri Kim, SuHyun Yoon, Jee-Hyong Lee‡
WACV 2025
@InProceedings{wacv,
author = {Choi, Junsu and Lee, Jin-Seop and Kim, Noo-ri and Yoon, SuHyun and Lee, Jee-Hyong},
title = {Feature-Level and Spatial-Level Activation Expansion for Weakly-Supervised Semantic Segmentation},
booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
month = {February},
year = {2025},
pages = {8701-8711}
}
|
2024 |
|
|
[C3] IGNORE: Information Gap-based False Negative Loss Rejection for Single Positive Multi-Label Learning
Gyeong Ryeol Song, Noo-ri Kim, Jin-Seop Lee, Jee-Hyong Lee‡
ECCV 2024
@InProceedings{ignore,
author="Song, GyeongRyeol
and Kim, Noo-ri
and Lee, Jin-Seop
and Lee, Jee-Hyong",
editor="Leonardis, Ale{\v{s}}
and Ricci, Elisa
and Roth, Stefan
and Russakovsky, Olga
and Sattler, Torsten
and Varol, G{\"u}l",
title="IGNORE: Information Gap-Based False Negative Loss Rejection for Single Positive Multi-Label Learning",
booktitle="Computer Vision -- ECCV 2024",
year="2025",
publisher="Springer Nature Switzerland",
address="Cham",
pages="472--488",
isbn="978-3-031-72754-2",
series={Lecture Notes in Computer Science},
volume={15092},
doi={10.1007/978-3-031-72754-2_27},
url={https://link.springer.com/chapter/10.1007/978-3-031-72754-2_27}
}
|
|
|
[C2] ExMatch: Semi-Supervised Learning with Scarce Labeled Samples with Additional Exploitation of Unlabeled Samples
Noo-ri Kim, Jin-Seop Lee, Jee-Hyong Lee‡
ECCV 2024
@InProceedings{exmatch,
author="Kim, Noo-ri
and Lee, Jin-Seop
and Lee, Jee-Hyong",
editor="Leonardis, Ale{\v{s}}
and Ricci, Elisa
and Roth, Stefan
and Russakovsky, Olga
and Sattler, Torsten
and Varol, G{\"u}l",
title="ExMatch: Self-guided Exploitation for Semi-supervised Learning with Scarce Labeled Samples",
booktitle="Computer Vision -- ECCV 2024",
year="2025",
publisher="Springer Nature Switzerland",
address="Cham",
pages="125--142",
isbn="978-3-031-73013-9",
series={Lecture Notes in Computer Science},
volume={15143},
doi={10.1007/978-3-031-73013-9_8},
url={https://link.springer.com/chapter/10.1007/978-3-031-73013-9_8}
}
|
|
|
[C1] Learning with Structural Labels in Learning with Noisy Labels
Noo-ri Kim*, Jin-Seop Lee*, Jee-Hyong Lee‡
CVPR 2024
@InProceedings{structural,
author = {Kim, Noo-ri and Lee, Jin-Seop and Lee, Jee-Hyong},
title = {Learning with Structural Labels for Learning with Noisy Labels},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
pages = {27610-27620}
}
|
|
|
[J2] Automation of Trimming Die Design Inspection by Zigzag Process Between AI and CAD Domains
Jin-Seop Lee*, Tae-Hyun Kim*, Sang-Hwan Jeon, Sung-Hyun Park, Sang-Hi Kim, Eun-Ho Lee‡, Jee-Hyong Lee‡
EAAI(Engineering Applications of Artificial Intelligence) 2024 - TOP 3%, IF 8.0
@article{zigzag,
title = {Automation of trimming die design inspection by zigzag process between AI and CAD domains},
author = {Lee, Jin-Seop and Kim, Tae-Hyun and Jeon, Sang-Hwan and Park, Sung-Hyun and Kim, Sang-Hi and Lee, Eun-Ho and Lee, Jee-Hyong},
journal = {Engineering Applications of Artificial Intelligence},
volume = {127},
pages = {107283},
year = {2024},
doi = {10.1016/j.engappai.2023.107283},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0952197623014677}
}
arXiv 2305.16866
|
2023 |
|
|
[J1] Automatic defect classification using semi-supervised learning with defect localization
Yusung Kim, Jin-Seop Lee, Jee-Hyong Lee
IEEE Transactions on Semiconductor Manufacturing 2023
@article{adc,
title = {Automatic Defect Classification Using Semi-Supervised Learning With Defect Localization},
author = {Kim, Yusung and Lee, Jin-Seop and Lee, Jee-Hyong},
journal = {IEEE Transactions on Semiconductor Manufacturing},
year = {2023},
volume = {36},
number = {3},
pages = {476--485},
doi = {10.1109/TSM.2023.3278036},
url = {https://doi.org/10.1109/TSM.2023.3278036}
}
|
EducationSungkyunkwan University (SKKU), South KoreaIntegrated M.S. and Ph.D., Artificial Intelligence Mar. 2021 - present Sungkyunkwan University (SKKU), South KoreaB.S., Mechanical Engineering / Computer Engineering (Double Major) Mar. 2015 - Feb. 2021 Incheon Science High School, South Korea Mar. 2013 - Feb. 2015 |
HonorsBest Paper Award, 2026 Summer Annual Conference of the Korean Artificial Intelligence Association (KAIA) Paper: PivotBench: Benchmarking LLM Agent Adaptation to Mid-task User Interventions Aug. 2026 Compute Gold Star (0.4%), CVPR 2026Distinguished recognition for transparent compute reporting and outstanding research contribution Jun. 2026 Winner, NRF Ph.D. Fellowship, National Research Foundation of Korea Title: Development Core Technology for Efficient Reasoning of Multimodal Generative AI Models Sep. 2025 – Aug. 2027 |
ReviewerConferences: CVPR (2024–), ICCV (2025–), ECCV (2024–), WACV (2024–), BMVC (2025–), AAAI (2025–), ARR (2025–), NeurIPS (2026–), ICML (2026–), ICLR (2026–), ACM SAC (2024–) Journals: International Journal of Computer Vision (2026–) |
|