Woo, Sunghyeon

6 publications

NeurIPS 2025 HiFC: High-Efficiency Flash-Based KV Cache Swapping for Scaling LLM Inference Inho Jeong, Sunghyeon Woo, Sol Namkung, Dongsuk Jeon

ICLR 2025 PaCA: Partial Connection Adaptation for Efficient Fine-Tuning Sunghyeon Woo, Sol Namkung, Sunwoo Lee, Inho Jeong, Beomseok Kim, Dongsuk Jeon

ICLR 2024 ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models Sunghyeon Woo, Sunwoo Lee, Dongsuk Jeon

NeurIPS 2024 DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation Sunghyeon Woo, Baesung Park, Byeongwook Kim, Minjung Jo, Se Jung Kwon, Dongsuk Jeon, Dongsoo Lee

ICLR 2023 Learning with Auxiliary Activation for Memory-Efficient Training Sunghyeon Woo, Dongsuk Jeon

NeurIPS 2021 Activation Sharing with Asymmetric Paths Solves Weight Transport Problem Without Bidirectional Connection Sunghyeon Woo, Jeongwoo Park, Jiwoo Hong, Dongsuk Jeon