Han, Dongsu

5 publications

WACV 2025 NarrAD: Automatic Generation of Audio Descriptions for Movies with Rich Narrative Context Jaehyeong Park, Junchel Ye, Seungkook Lee, Hyun W. Ka, Dongsu Han

NeurIPS 2025 SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs Jinwoo Park, Seunggeun Cho, Dongsu Han

ICML 2024 Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training Yechan Kim, Hwijoon Lim, Dongsu Han

CVPR 2023 AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration Juncheol Ye, Hyunho Yeo, Jinwoo Park, Dongsu Han

ICML 2022 TSPipe: Learn from Teacher Faster with Pipelines Hwijoon Lim, Yechan Kim, Sukmin Yun, Jinwoo Shin, Dongsu Han