5 citations · 6 across the 6 of their papers we have counts for
7 papers
Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
Seungcheol Park, Jeongin Bae, Beomseok Kwon +5
How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (B…
Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information
Seungcheol Park, Sojin Lee, Jongjin Kim +3
How can we accelerate large language models(LLMs) without sacrificing accuracy? The slow inference speed of LLMs hinders us to benefit from their remarkable performance in diverse…
A Comprehensive Survey of Compression Algorithms for Language Models
Seungcheol Park, Jaehyeon Choi, Sojin Lee +1
How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable advances of…
Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
Seungcheol Park, Hojun Choi, U Kang
Given a pretrained encoder-based language model, how can we accurately compress it without retraining? Retraining-free structured pruning algorithms are crucial in pretrained langu…
Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation
Seung Ho Park, Young Su Moon, Nam Ik Cho
Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-ori…
Flexible Style Image Super-Resolution using Conditional Objective
Seung Ho Park, Young Su Moon, Nam Ik Cho
Recent studies have significantly enhanced the performance of single-image super-resolution (SR) using convolutional neural networks (CNNs). While there can be many high-resolution…
Fast and Accurate Transferability Measurement for Heterogeneous Multivariate Data
Seungcheol Park, Huiwen Xu, Taehun Kim +3
Given a set of heterogeneous source datasets with their classifiers, how can we quickly find the most useful source dataset for a specific target task? We address the problem of me…