← Search

Beom Jin Kang

2 accepted papers

2025

GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocation

EMNLP 2025

Large-scale models have achieved state-of-the-art performance in automatic speech recognition (ASR), but their high memory and computation demands pose significant challenges for deployment. To address these challenges, weight-only quantization is widely adopted in large-scale models, where weights

Cited by 0SourcePDFScholar
2025

LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers

ICML 2025poster

Recently, transformer-based models have demonstrated state-of-the-art performance across various computer vision tasks, including image classification, detection, and segmentation. However, their substantial parameter count poses significant challenges for deployment in resource-constrained environm…

Cited by 0SourcePDFScholar