Scholar
Dahun Kim
Google Scholar ID: mHpN1xoAAAAJ
Research Scientist, Google DeepMind
Citations & Impact
Citations
3,323
H-index
24
i10-index
35
Publications
20
Co-authors
27
list available
Publications
Resume (English only)
Academic Achievements
- [{'Type': 'Paper', 'Title': 'EmbeddingGemma: Powerful and Lightweight Text Representations', 'Authors': 'Gemini Embedding Team, Google', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment', 'Authors': 'Dahun Kim, Anelia Angelova', 'Conference': 'COLM 2025', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities', 'Authors': 'Gemini Team, Google', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Time-Scaling State-Space Models for Dense Video Captioning', 'Authors': 'AJ Piergiovanni, Ganesh Mallya, Dahun Kim, Anelia Angelova', 'Conference': 'BMVC 2025', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models', 'Authors': 'Dahun Kim, AJ Piergiovanni, Ganesh Mallya, Anelia Angelova', 'Conference': 'CVPR 2025', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications', 'Authors': 'Ganesh Mallya, Yotam Gigi, Dahun Kim, Maxim Neumann, Genady Beryozkin, Tomer Shekel, Anelia Angelova', 'Conference': 'AGU 2025', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning', 'Authors': 'AJ Piergiovanni, Dahun Kim, Michael S Ryoo, Isaac Noble, Anelia Angelova', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Learning Visual Grounding from Generative Vision and Language Model', 'Authors': 'Shijie Wang, Dahun Kim, Ali Taalimi, Chen Sun, Weicheng Kuo', 'Conference': 'WACV 2025', 'Year': '2025'}, {'Type': 'Paper', 'Title': 'Region-centric Image-Language Pretraining for Open-Vocabulary Detection', 'Authors': 'Dahun Kim, Anelia Angelova, Weicheng Kuo', 'Conference': 'ECCV 2024', 'Year': '2024'}, {'Type': 'Paper', 'Title': 'Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation', 'Authors': 'Minsu Kim, Jeongsoo Choi, Dahun Kim, Yong Man Roh', 'Journal': 'TASLP 2024', 'Year': '2024'}, {'Type': 'Paper', 'Title': 'Omnibind: Teach to build unequal-scale modality interaction for omni-bind of all', 'Authors': 'Yuanhuiyi Lyu, Xu Zheng, Dahun Kim, Lin Wang', 'Year': '2024'}]
Research Experience
- [{'Company': 'Google DeepMind (formerly Google Brain)', 'Position': 'Senior Research Scientist / Research Scientist', 'Period': 'July 2022 - Present', 'Collaborators': ''}, {'Company': 'Google Research', 'Position': 'Research Intern', 'Period': 'May 2021 - January 2022', 'Collaborators': 'Liang-Chieh Chen, Jun Xie'}, {'Company': 'Google Brain', 'Position': 'Research Intern', 'Period': 'June 2020 - November 2020', 'Collaborators': 'Weicheng Kuo, Tsung-Yi Lin, Anelia Angelova'}, {'Company': 'Adobe Research', 'Position': 'Research Intern', 'Period': 'June 2019 - September 2019', 'Collaborators': 'Joon-Young Lee'}, {'Institution': 'KAIST', 'Position': 'Research Assistant', 'Lab': 'Robotics and Computer Vision Lab', 'Period': 'March 2016 - February 2022'}]
Background
- A Senior Research Scientist at Google DeepMind. His recent research interests focus on improving the capabilities of Large Multimodal Models (e.g., Gemini) and understanding the interaction between vision and language.
Miscellany
- Academic activities include serving as an Area Chair in NeurIPS 2025, 2024, 2023, ICML 2025, CVPR 2026, 2025, 2024, 2023; Action Editor of Transactions on Machine Learning Research (TMLR); Outstanding Reviewer in CVPR 2021, ECCV 2020; and reviewer for multiple top conferences and journals.
