Se Jung Kwon
Identifiers
- name variant Se Jung Kwon 0.60 · backfill
Papers (27)
- SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification cs.CL · 2025 · author #7
- Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models cs.CL · 2025 · author #6
- Faster Inference of LLMs using FP8 on the Intel Gaudi cs.AR · 2025 · author #11
- An Inquiry into Datacenter TCO for LLM Inference with FP8 cs.LG · 2025 · author #5
- Debunking the CUDA Myth Towards GPU-based AI Systems cs.DC · 2024 · author #11
- LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices cs.LG · 2024 · author #4
- To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability cs.LG · 2024 · author #4
- HyperCLOVA X Technical Report cs.CL · 2024 · author #13
- No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization cs.LG · 2024 · author #7
- DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation cs.LG · 2024 · author #5
- Label-Noise Robust Diffusion Models cs.LG · 2024 · author #5
- Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models cs.LG · 2023 · author #5
- FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization cs.LG · 2023 · author #3
- Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization cs.LG · 2023 · author #6
- Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models cs.CV · 2022 · author #3
- AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models cs.LG · 2022 · author #1
- LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models cs.DC · 2022 · author #7
- Maximum Likelihood Training of Implicit Nonlinear Diffusion Models cs.LG · 2022 · author #3
- Modulating Regularization Frequency for Efficient Compression-Aware Model Training cs.LG · 2021 · author #2
- Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression cs.LG · 2021 · author #2
- Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization cs.LG · 2021 · author #5
- Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation cs.LG · 2020 · author #4
- FleXOR: Trainable Fractional Quantization cs.LG · 2020 · author #2
- BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs cs.LG · 2020 · author #3
- Learning Low-Rank Approximation for CNNs cs.LG · 2019 · author #2
- Structured Compression by Weight Encryption for Unstructured Pruning and Quantization cs.LG · 2019 · author #1
- Network Pruning for Low-Rank Binary Indexing cs.LG · 2019 · author #2
Mentions
- 2502.01070 #5 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2506.03781 #6 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2309.15531 #5 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2405.18710 #4 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2501.00210 #11 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2503.09975 #11 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2402.17812 #5 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2407.11534 #4 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2306.00317 #3 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2404.01954 #13 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2206.09557 #7 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2402.18096 #7 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2402.17517 #5 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2305.14152 #6 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2211.17091 #3 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2205.13699 #3 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2210.03858 #1 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2105.01869 #2 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2105.01875 #2 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2105.01868 #5 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2009.04126 #2 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2009.07453 #4 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2005.09904 #3 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 1905.10138 #1 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 1905.10145 #2 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 1905.05686 #2 · arxiv_oai · confidence 0.70 Se Jung Kwon
- 2510.02329 #7 · arxiv_oai · confidence 0.70 Se Jung Kwon
Frequent Coauthors
- Dongsoo Lee 25 shared papers
- Byeongwook Kim 19 shared papers
- Baeseong Park 11 shared papers
- Jeonghoon Kim 7 shared papers
- Joonhyung Lee 6 shared papers
- Beomseok Kwon 5 shared papers
- Jeongin Bae 5 shared papers
- Jung Hyun Lee 5 shared papers
- Yongkweon Jeon 5 shared papers
- Gunho Park 4 shared papers
- Kang Min Yoo 4 shared papers
- Gu-Yeon Wei 3 shared papers
- Il-Chul Moon 3 shared papers
- Jeongin Yun 3 shared papers
- Minsub Kim 3 shared papers
- Sungjae Lee 3 shared papers
- Wanmo Kang 3 shared papers
- Byeonghu Na 2 shared papers
- Daehwan Oh 2 shared papers
- Dongjun Kim 2 shared papers