← Authors

Dongsoo Lee

17 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (27) 🀝 Dynamic Duo (14) πŸ‘‘ Triple Crown 🌱 Topic Pioneer πŸ—ƒοΈ Keyword Collector (53) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ’Ž Century Club (17)

Conferences

ICLR (6) NIPS (5) EMNLP (2) ACL (1) CVPR (1) ICML (1) NAACL (1)

Top co-authors

Se Jung Kwon (14) Byeongwook Kim (10) Jeonghoon Kim (7) Baeseong Park (6) Beomseok Kwon (3) Kang Min Yoo (3) Jae-Joon Kim (3) Jung Hyun Lee (3) Jeongin Bae (2) Yongkweon Jeon (2)

Keywords

model compression (7) large language model (4) neural network optimization (4) weight quantization (4) parameter-efficient fine-tuning (3) binary quantization (2) post-training quantization (2) knowledge distillation (1) low-rank approximation (1) neural encoding (1) network pruning (1) maximum likelihood (1) fisher information (1) parameter sharing (1) population coding (1) information geometry (1) training efficiency (1) neural machine translation (1) generative model (1) parameter optimization (1)

Papers

Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models ACL 2025
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices NAACL 2025
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models ICLR 2024
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation NIPS 2024
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models ICLR 2024
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization NIPS 2023
Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic ICLR 2023
Information Geometry of the Retinal Representation Manifold NIPS 2023
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization ICML 2023
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models EMNLP 2022
Maximum Likelihood Training of Implicit Nonlinear Diffusion Model NIPS 2022
Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression ICLR 2022
FleXOR: Trainable Fractional Quantization NIPS 2020
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation EMNLP 2020
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization CVPR 2020
Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network ICLR 2019
Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression Ratio ICLR 2018