Daegun Yoon - RankMe

18 papers B 2Misc 1Journal 13Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing. CoRR Myunghyun Rhee, Joonseop Sim, Taeyoung Ahn, Seungyong Lee, Daegun Yoon, Euiseok Kim, Kyoung Park, Youngpyo Joo, Hosik Kim
2025	J	`jnl`	StreamDQ: HBM-Integrated On-the-Fly DeQuantization via Memory Load for Large Language Models. IEEE Comput. Archit. Lett. Minki Jeong, Daegun Yoon, Soohong Ahn, Seungyong Lee, Jooyoung Kim, Jinuk Jeon, Joonseop Sim, Youngpyo Joo, Hoshik Kim
2024	B	`conf`	Preserving Near-Optimal Gradient Sparsification Cost for Scalable Distributed Deep Learning. CCGrid Daegun Yoon, Sangyoon Oh
2024	J	`jnl`	Preserving Near-Optimal Gradient Sparsification Cost for Scalable Distributed Deep Learning. CoRR Daegun Yoon, Sangyoon Oh
2023	—	`conf`	Can hierarchical client clustering mitigate the data heterogeneity effect in federated learning? IPDPS Workshops Seungjun Lee, Miri Yu, Daegun Yoon, Sangyoon Oh
2023	B	`conf`	DEFT: Exploiting Gradient Norm Difference between Model Layers for Scalable Gradient Sparsification. ICPP Daegun Yoon, Sangyoon Oh
2023	J	`jnl`	DEFT: Exploiting Gradient Norm Difference between Model Layers for Scalable Gradient Sparsification. CoRR Daegun Yoon, Sangyoon Oh
2023	Misc	`conf`	MiCRO: Near-Zero Cost Gradient Sparsification for Scaling and Accelerating Distributed DNN Training. HiPC Daegun Yoon, Sangyoon Oh
2023	J	`jnl`	MiCRO: Near-Zero Cost Gradient Sparsification for Scaling and Accelerating Distributed DNN Training. CoRR Daegun Yoon, Sangyoon Oh
2023	J	`jnl`	SAGE: toward on-the-fly gradient compression ratio scaling. J. Supercomput. Daegun Yoon, Minjoong Jeong, Sangyoon Oh
2023	J	`jnl`	WAVE: designing a heuristics-based three-way breadth-first search on GPUs. J. Supercomput. Daegun Yoon, Minjoong Jeong, Sangyoon Oh
2022	J	`jnl`	AMBLE: Adjusting mini-batch and local epoch for federated learning with heterogeneous devices. J. Parallel Distributed Comput. Juwon Park, Daegun Yoon, Sangho Yeo, Sangyoon Oh
2022	J	`jnl`	Empirical Analysis on Top-k Gradient Sparsification for Distributed Deep Learning in a Supercomputing Environment. CoRR Daegun Yoon, Sangyoon Oh
2022	J	`jnl`	SURF: Direction-Optimizing Breadth-First Search Using Workload State on GPUs. Sensors Daegun Yoon, Sangyoon Oh
2021	J	`jnl`	Balanced content space partitioning for pub/sub: a study on impact of varying partitioning granularity. J. Supercomput. Daegun Yoon, Zhetao Li, Sangyoon Oh
2021	J	`jnl`	Exploring a system architecture of content-based publish/subscribe system for efficient on-the-fly data dissemination. Concurr. Comput. Pract. Exp. Daegun Yoon, Gyudong Park, Sangyoon Oh
2021	J	`jnl`	Mitigating Cold Start Problem in Serverless Computing with Function Fusion. Sensors Seungjun Lee, Daegun Yoon, Sangho Yeo, Sangyoon Oh
2020	—	`conf`	CPartition: a Correlation-Based Space Partitioning for Content-Based Publish/Subscribe Systems with Skewed Workload. BigComp Daegun Yoon, Gyudong Park, Sangyoon Oh