Daehyeon Baek

According to our database, Daehyeon Baek authored at least 7 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

FireQ: Fast INT4-FP8 Kernel and RoPE-aware Quantization for LLM Inference Acceleration.

Daehyeon Baek, Jieun Choi, Jimyoung Son, Kyungmin Bin, Seungbeom Choi, Kihyo Moon, Minsung Jang, Hyojung Lee

CoRR, May, 2025

PAISE: PIM-Accelerated Inference Scheduling Engine for Transformer-based LLM.

Hyojung Lee, Daehyeon Baek, Jimyoung Son, Jieun Choi, Kihyo Moon, Minsung Jang

Proceedings of the IEEE International Symposium on High Performance Computer Architecture, 2025

2024

Cerberus: Triple Mode Acceleration of Sparse Matrix and Vector Multiplication.

Soojin Hwang, Daehyeon Baek, Jongse Park, Jaehyuk Huh

ACM Trans. Archit. Code Optim., June, 2024

pSyncPIM: Partially Synchronous Execution of Sparse Matrix Operations for All-Bank PIM Architectures.

Daehyeon Baek, Soojin Hwang, Jaehyuk Huh

Proceedings of the 51st ACM/IEEE Annual International Symposium on Computer Architecture, 2024

2021

DNN Model Deployment on Distributed Edges.

Eunho Cho, Juyeon Yoon, Daehyeon Baek, Dongman Lee, Doo-Hwan Bae

Proceedings of the ICWE 2021 Workshops, 2021

InnerSP: A Memory Efficient Sparse Matrix Multiplication Accelerator with Locality-Aware Inner Product Processing.

Daehyeon Baek, Soojin Hwang, Taekyung Heo, Daehoon Kim, Jaehyuk Huh

Proceedings of the 30th International Conference on Parallel Architectures and Compilation Techniques, 2021

2020

Charge-Aware DRAM Refresh Reduction with Value Transformation.

Seikwon Kim, Wonsang Kwak, Changdae Kim, Daehyeon Baek, Jaehyuk Huh

Proceedings of the IEEE International Symposium on High Performance Computer Architecture, 2020