Diving into a Spectrum of Projects, Ideas, and Progress.
2025-04-08 ~ 2025-05-28
👉 Paper 👉 Project Page Abstract This project presents an end-to-end framework for automatically understanding video content and generating aligned multimedia outputs. The proposed system analyzes visual semantics from input videos and produces structured representations that enable downstream generation and evaluation. Our approach demonstrates robust performance across diverse video scenarios,...
2024-08-05 ~ 2025-02-12
Overview During the Naver AI Tech 7th (Computer Vision Track), I conducted four major projects ranging from image classification to segmentation. Through this intensive curriculum, I developed expertise in Data-Centric AI, Model Optimization, and MLOps tools (WandB, Poetry). Below is a summary of the key projects and my specific contributions....
2025-01-02 ~ 2025-02-12
Overview of the proposed model architecture. 👉 Code 👉 Report Objective With the integration and pretraining of audio adapters, large language models have become capable of understanding diverse audio signals—such as speech, music, and environmental sounds—and performing a wide range of downstream tasks. However, in typical device environments with limited...
2023-05-02 ~ 2023-09-25
교육기관: DIP(Daegu Digital Innovation Promotion) 👉 Paper 👉 Project Page