Baeseong Park
6 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (12) π Cross-Pollinator (15) π Interdisciplinary Bridge π Conference Polyglot (4) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π±
Topic Pioneer
Conferences
EMNLP (2)
ICLR (2)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
model compression
(4)
weight quantization
(2)
neural network optimization
(2)
network pruning
(1)
parameter-efficient fine-tuning
(1)
parameter efficient fine-tuning
(1)
edge device
(1)
sparse neural network
(1)
low-bit quantization
(1)
on-device inference
(1)
mixed precision
(1)
binary neural network
(1)
unstructured pruning
(1)
mixed precision quantization
(1)
large language model
(1)
weight encryption
(1)
binary quantization
(1)
transformer quantization
(1)
binary coding quantization
(1)
xor network
(1)
Papers
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
ICLR 2024
Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic
ICLR 2023
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models
EMNLP 2022
FleXOR: Trainable Fractional Quantization
NIPS 2020
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
CVPR 2020
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation
EMNLP 2020