Profiles2022-2024
Jung Kwon
NAVER Cloud
6Papers
1Last author
21Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers6
- LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language ModelsAuthor 7 of 10ICLR 2024 · 134 citations
- Label-Noise Robust Diffusion ModelsAuthor 5 of 8ICLR 2024 · 20 citations
- Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer QuantizationAuthor 7 of 7NeurIPS 2023 · 157 citations
- Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer ArithmeticAuthor 8 of 10ICLR 2023
- AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language ModelsAuthor 1 of 14EMNLP Findings 2022 · 13 citations
- Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model CompressionAuthor 2 of 5ICLR 2022 · 4 citations
