"au:"Seungwoo Son"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Seungwoo Son"" — arXiv2 Search

Showing 1–5 of 5 results

/ Date/ Name

Jun 17, 2024Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization Feb 21, 2023The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers Feb 7, 2026On the Importance of a Multi-Scale Calibration for Quantization Feb 4, 2026TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation Feb 2, 2026Two-Stage Grid Optimization for Group-wise Quantization of LLMs