Geewook Kim

41 papers A* 7A 1B 1Journal 21Unranked 11
YearRankTypeTitle / Venue / Authors
2026 — conf
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact.
EACL (Volume 1: Long Papers)
Hyunji Lee, Seunghyun Yoon, Yunjae Won, Hanseok Oh, Geewook Kim, Trung Bui, Franck Dernoncourt, Elias Stengel-Eskin, Mohit Bansal, Minjoon Seo
2026 A* conf
State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models.
AAAI
Geewook Kim, Minjoon Seo
2025 J jnl
Context-Informed Grounding Supervision.
CoRR
Hyunji Lee, Seunghyun Yoon, Yunjae Won, Hanseok Oh, Geewook Kim, Trung Bui, Franck Dernoncourt, Elias Stengel-Eskin, Mohit Bansal, Minjoon Seo
2025 J jnl
Does Audio Matter for Modern Video-LLMs and Their Benchmarks?
CoRR
Geewook Kim, Minjoon Seo
2025 — conf
Evaluating Multimodal Generative AI with Korean Educational Standards.
NAACL (Short Papers)
Sanghee Park, Geewook Kim
2025 J jnl
Evaluating Multimodal Generative AI with Korean Educational Standards.
CoRR
Sanghee Park, Geewook Kim
2025 A* conf
How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
ICLR
Seongyun Lee, Geewook Kim, Jiyeon Kim, Hyunji Lee, Hoyeon Chang, Sue Hyun Park, Minjoon Seo
2025 — conf
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models.
ACL (Findings)
Gio Paik, Geewook Kim, Jinbae Im
2025 J jnl
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models.
CoRR
Gio Paik, Geewook Kim, Jinbae Im
2025 J jnl
MambaMia: A State-Space-Model-Based Compression for Efficient Video Understanding in Large Multimodal Models.
CoRR
Geewook Kim, Minjoon Seo
2024 — conf
CREPE: Coordinate-Aware End-to-End Document Parser.
ICDAR (4)
Yamato Okamoto, Youngmin Baek, Geewook Kim, Ryota Nakao, Donghyun Kim, Moonbin Yim, Seunghyun Park, Bado Lee
2024 J jnl
CREPE: Coordinate-Aware End-to-End Document Parser.
CoRR
Yamato Okamoto, Youngmin Baek, Geewook Kim, Ryota Nakao, Donghyun Kim, Moonbin Yim, Seunghyun Park, Bado Lee
2024 J jnl
How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
CoRR
Seongyun Lee, Geewook Kim, Jiyeon Kim, Hyunji Lee, Hoyeon Chang, Sue Hyun Park, Minjoon Seo
2024 A* conf
On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning.
EMNLP
Geewook Kim, Minjoon Seo
2024 J jnl
On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning.
CoRR
Geewook Kim, Minjoon Seo
2024 — conf
Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation.
ACL (Findings)
Seongyun Lee, Seungone Kim, Sue Hyun Park, Geewook Kim, Minjoon Seo
2024 J jnl
Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation.
CoRR
Seongyun Lee, Seungone Kim, Sue Hyun Park, Geewook Kim, Minjoon Seo
2023 J jnl
Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models.
CoRR
Geewook Kim, Hodong Lee, Daehee Kim, Haeji Jung, Sanghee Park, Yoonsik Kim, Sangdoo Yun, Taeho Kil, Bado Lee, Seunghyun Park
2023 — conf
On Text Localization in End-to-End OCR-Free Document Understanding Transformer Without Text Localization Supervision.
ICDAR Workshops (1)
Geewook Kim, Shuhei Yokoo, Sukmin Seo, Atsuki Osanai, Yamato Okamoto, Youngmin Baek
2023 — conf
On Web-based Visual Corpus Construction for Visual Document Understanding.
ICDAR (3)
Donghyun Kim, Teakgyu Hong, Moonbin Yim, Yoonsik Kim, Geewook Kim
2023 A* conf
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap.
ICCV
Daehee Kim, Yoonsik Kim, Donghyun Kim, Yumin Lim, Geewook Kim, Taeho Kil
2023 J jnl
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap.
CoRR
Daehee Kim, Yoonsik Kim, Donghyun Kim, Yumin Lim, Geewook Kim, Taeho Kil
2023 A* conf
Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models.
EMNLP
Geewook Kim, Hodong Lee, Daehee Kim, Haeji Jung, Sanghee Park, Yoonsik Kim, Sangdoo Yun, Taeho Kil, Bado Lee, Seunghyun Park
2022 — conf
OCR-Free Document Understanding Transformer.
ECCV (28)
Geewook Kim, Teakgyu Hong, Moonbin Yim, JeongYeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park
2022 J jnl
On Web-based Visual Corpus Construction for Visual Document Understanding.
CoRR
Donghyun Kim, Teakgyu Hong, Moonbin Yim, Yoonsik Kim, Geewook Kim
2022 J jnl
Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching.
CoRR
Geewook Kim, Wonseok Hwang, Minjoon Seo, Seunghyun Park
2021 — conf
Cost-effective End-to-end Information Extraction for Semi-structured Document Images.
EMNLP (1)
Wonseok Hwang, Hyunji Lee, Jinyeong Yim, Geewook Kim, Minjoon Seo
2021 J jnl
Cost-effective End-to-end Information Extraction for Semi-structured Document Images.
CoRR
Wonseok Hwang, Hyunji Lee, Jinyeong Yim, Geewook Kim, Minjoon Seo
2021 J jnl
Donut: Document Understanding Transformer without OCR.
CoRR
Geewook Kim, Teakgyu Hong, Moonbin Yim, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park
2021 J jnl
Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings.
CoRR
Masahiro Naito, Sho Yokoi, Geewook Kim, Hidetoshi Shimodaira
2020 B conf
Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model.
COLING
Sungrae Park, Geewook Kim, Junyeop Lee, Junbum Cha, Ji-Hoon Kim, Hwalsuk Lee
2020 J jnl
Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization.
CoRR
Morihiro Mizutani, Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira
2019 A conf
Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability.
AISTATS
Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira
2019 A* conf
Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities.
IJCAI
Geewook Kim, Akifumi Okuno, Kazuki Fukui, Hidetoshi Shimodaira
2019 J jnl
Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities.
CoRR
Geewook Kim, Akifumi Okuno, Kazuki Fukui, Hidetoshi Shimodaira
2019 — conf
Segmentation-free compositional n-gram embedding.
NAACL-HLT (1)
Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira
2019 A* conf
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis.
ICCV
Jeonghun Baek, Geewook Kim, Junyeop Lee, Sungrae Park, Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Hwalsuk Lee
2019 J jnl
What is wrong with scene text recognition model comparisons? dataset and model analysis.
CoRR
Jeonghun Baek, Geewook Kim, Junyeop Lee, Sungrae Park, Dongyoon Han, Sangdoo Yun, Seong Joon Oh, Hwalsuk Lee
2018 J jnl
Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability.
CoRR
Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira
2018 J jnl
Segmentation-free compositional n-gram embedding.
CoRR
Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira
2018 — conf
Word-like character n-gram embedding.
NUT@EMNLP
Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira