- 일시: 2025년 8월 5일(화) 오전 10시
- 연사: 김홍회 Machine Learning Engineer(Samsung Research America)
- 제목: Introduction to Vision-Language Models (VLM) and Language Models (LLM): Understanding On-Device Solutions
- ABSTRACT
Vision-Language Models (VLMs)
and Language Models (LLMs) have emerged as highly effective tools for
comprehending both visual and textual data. Recent advancements in these models
have paved the way for their integration into practical applications where they
can be utilized directly on devices. This presentation aims to introduce the
fundamentals of VLMs and LLMs and showcase their potential uses in various
on-device scenarios.
- BIOGRAPHY
Dr. Hong-hoe (Ayden) Kim is a Machine Learning Engineer at Samsung
Research America. He specializes in developing large language model (LLM)
solutions tailored for on-device applications. Dr. Kim earned his Ph.D. from
Texas A&M University and has served as a member of the program committees
for various ACM conferences.
- 주관: 남창주 교수 연구실