Publications

2026

CoRT: Supporting Hard and Soft Real-Time Tasks in Batched LLM Serving

Yeongwoo Ha*, Taemin Kim*, Changhun Han, Chan Heo, Jaeheon Kwak, Hyosu Kim, Kilho Lee, Hoon Sung Chwa, and Sangeun Oh†. ICCAD 2026. Paper forthcoming.
Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks

Wonyong Cho*, Taemin Kim*, Jungmin Kim, Jeong Rae Kim, and Sung Hoon Jung. arXiv, 2026.
TipMate: An Explainable Fair Tip Recommender System based on LLM

Taemin Kim, Junhyuk Seo, Hyejung Ko, Keejun Han, and Woonghee Lee†. IEEE Access, 2026.
Zero-Shot Voice Cloning Based Emotion-Preserving Video Dubbing

Junhyuk Seo*, Taemin Kim*, Hyejung Ko*, and Heeseok Oh†. IEIE Journal, 2026.

Evaluating Generalization and Data Leakage in Large Language Models via Data Perturbation

Taemin Kim* and Seoklea Cho*. IEIE Conference, 2025.
Exploring Modular Prompt Design for Emotion and Mental Health Recognition

Minseo Kim*, Taemin Kim*, Thu Hoang Anh Vo, Yugyeong Jung†, and Uichin Lee†. CHI Conference, 2025.

Efficient Generative Multimodal Integration (EGMI): Enabling Audio Generation from Text-Image Pairs through Alignment with Large Language Models

Taemin Kim*, Wooyeol Baek*, and Heeseok Oh†. NeurIPS Workshop, 2024.
Improving Instance Representation in Personalized Image Generation with Optimized Attention Mechanism and Text Encoder

Taemin Kim*, Hyejung Ko*, Wooyeol Baek, and Heeseok Oh†. IEIE Conference, 2024.

* Equal contribution. † Corresponding author.