Scholar
Yeonhong Park
Google Scholar ID: eZN-njgAAAAJ
Seoul National University
Citations & Impact
Citations
713
H-index
8
i10-index
8
Publications
16
Co-authors
0
Publications
Resume
Academic Achievements
- [OSDI '25] DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization
- [ICML '25] FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
- [ICML '25] GuidedQuant: Large Language Model Quantization via Exploiting End-to-End Loss Guidance
- [HPCA '25] FACIL: Flexible DRAM Address Mapping for SoC-PIM Cooperative On-device LLM Inference
- [ACCV '24] ReLUifying Smooth Functions: Low-Cost Knowledge Distillation to Obtain High-Performance ReLU Networks
- [ICML '24] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
- [APSys '23] Liquid: Mix-and-Match Multiple Image Formats to Balance DNN Training Pipeline
- [VLDB '22] Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
- [DAC '22] Effective Zero Compression on ReRAM-based Sparse DNN Accelerators
- [HPCA '22] Mithril: Cooperative Row Hammer Protection on Commodity DRAM Leveraging Managed Refresh
- [ISCA '21] BOSS: Bandwidth-Optimized Search Accelerator for Storage-Class Memory
- [HPCA '21] Layerweaver: Maximizing Resource Utilization of Neural Processing Units via Layer-Wise Scheduling
- [ICCAD '20] Unlocking Wordline-level Parallelism for Fast Inference on RRAM-based DNN Accelerator
- [MICRO '20] Graphene: Strong yet Lightweight Row Hammer Protection
Background
- Postdoctoral researcher in ARC lab at Seoul National University. His current research focuses on systems for large-scale machine learning.