Scholar
Byeonggeun Kim
Google Scholar ID: Pee89n0AAAAJ
Sr. Applied Scientist at AGI, Amazon
Citations & Impact
Citations
596
H-index
9
i10-index
9
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Honors:
- - Alexa Perceptual Technology Award Q3/Q4 2023, Recognized for contribution to Large Language Models that raise the functional bar. Awarded by Amazon in Feb 2024.
- - Challenge Winner, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge, 2021
- Academic Services:
- - Session Chair: INTERSPEECH (2022)
- - Reviewer: INTERSPEECH (2023-2025), ICASSP (2023-2025), CVPR (2024-2026), ICCV (2025), WACV (2025, 2026), ACL (2025), AAAI (2025-2026), EMNLP (2025)
- - Invited Talk: Autoregressive text-to-audio generation approaches @ Amazon Media & Entertainment ML (+AI) Summit, Sep 30, 2025
Research Experience
- Amazon AGI (Artificial General Intelligence)
- - Senior Applied Scientist: Feb 2023 - Present
- - Applied Scientist II: Apr 2025 - Present
- - Applied Scientist: Feb 2023 - Mar 2025
- - Toronto, ON, Canada: Feb 2023 - Jul 2024
- Qualcomm AI Research
- - Staff AI Researcher: Nov 2022 - Jan 2023
- - Senior AI Researcher: Dec 2019 - Nov 2022
- - AI Researcher: Apr 2018 - Nov 2019, Seoul, South Korea
Education
- M.S.: Feb 2016 - Feb 2018, Korea Advanced Institute of Science and Technology (KAIST), Electrical Engineering, Dissertation: Knowledge base completion with translation based embeddings and negative sampling method, Advisor: Soo-Young Lee
- B.S.: Feb 2009 - Feb 2016, Korea Advanced Institute of Science and Technology (KAIST), Electrical Engineering, Double major in Business
Background
- Currently serving as a Senior Applied Scientist at Amazon AGI, specializing in developing audio foundation models for integration into multi-modal LLMs. Additionally, acts as the technical lead for audio generation solutions. Research interests lie in general machine learning/deep learning, with a particular emphasis on creating video or text conditioned audio generation solutions for MLLMs.
Miscellany
- Mandatory Military Service:
- - Sergeant, Jun 2010 - Mar 2012, Korea Augmentation To the United States Army (KATUSA)
