Segui
Young Jin Kim
Young Jin Kim
Microsoft, Georgia Tech. (CSE)
Email verificata su gatech.edu - Home page
Titolo
Citata da
Citata da
Anno
Prediction of weather-induced airline delays based on machine learning algorithms
S Choi, YJ Kim, S Briceno, D Mavris
Digital Avionics Systems Conference (DASC), 2016 IEEE/AIAA 35th, 2016
2092016
A deep learning approach to flight delay prediction
YJ Kim, S Choi, S Briceno, D Mavris
2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), 2016
1972016
How good are gpt models at machine translation? a comprehensive evaluation
A Hendy, M Abdelrehim, A Sharaf, V Raunak, M Gabr, H Matsushita, ...
arXiv preprint arXiv:2302.09210, 2023
1822023
Taming sparsely activated transformer with stochastic experts
S Zuo, X Liu, J Jiao, YJ Kim, H Hassan, R Zhang, T Zhao, J Gao
arXiv preprint arXiv:2110.04260, 2021
702021
Lower numerical precision deep learning inference and training
A Rodriguez, E Segal, E Meiri, E Fomenko, YJ Kim, H Shen, B Ziv
https://software.intel.com/en-us/articles/lower-numerical-precision-deep …, 2018
692018
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
YJ Kim, M Junczys-Dowmunt, H Hassan, AF Aji, K Heafield, ...
Proceedings of the 3rd Workshop on Neural Generation and Translation, 280-288, 2019
622019
Scalable and efficient moe training for multitask multilingual models
YJ Kim, AA Awan, A Muzio, AFC Salinas, L Lu, A Hendy, S Rajbhandari, ...
arXiv preprint arXiv:2109.10465, 2021
582021
FastFormers: Highly efficient transformer models for natural language understanding
YJ Kim, HH Awadalla
arXiv preprint arXiv:2010.13382, 2020
492020
Artificial neural network models for airport capacity prediction
S Choi, YJ Kim
Journal of Air Transport Management 97, 102146, 2021
352021
A paradigm shift in machine translation: Boosting translation performance of large language models
H Xu, YJ Kim, A Sharaf, HH Awadalla
arXiv preprint arXiv:2309.11674, 2023
252023
Cost-sensitive prediction of airline delays using machine learning
S Choi, YJ Kim, S Briceno, D Mavris
2017 IEEE/AIAA 36th Digital Avionics Systems, 2017
202017
Gating dropout: Communication-efficient regularization for sparsely activated transformers
R Liu, YJ Kim, A Muzio, H Hassan
International Conference on Machine Learning, 13782-13792, 2022
132022
Parallel Simulation of Agent-Based Model for Air Traffic Network
YJ Kim, OJ Pinon-Fischer, DN Mavris
AIAA Modeling and Simulation Technologies Conference, 2799, 2015
72015
Time-and space-parallel simulation of air traffic networks
YJ Kim, D Mavris, R Fujimoto
Simulation 95 (12), 1213-1228, 2019
62019
Finequant: Unlocking efficiency with fine-grained weight-only quantization for llms
YJ Kim, R Henry, R Fahim, HH Awadalla
arXiv preprint arXiv:2308.09723, 2023
52023
Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production
YJ Kim, R Henry, R Fahim, HH Awadalla
arXiv preprint arXiv:2211.10017, 2022
52022
Accelerating TensorFlow on Modern Intel Architectures
E Ould-Ahmed-Vall, M Abuzaina, MF Amin, J Bobba, RS Dubtsov, ...
International workshop on architectures for intelligent machines, 2017
52017
Contrastive preference optimization: Pushing the boundaries of llm performance in machine translation
H Xu, A Sharaf, Y Chen, W Tan, L Shen, B Van Durme, K Murray, YJ Kim
arXiv preprint arXiv:2401.08417, 2024
32024
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
G Jawahar, S Mukherjee, X Liu, YJ Kim, M Abdul-Mageed, ...
arXiv preprint arXiv:2210.07535, 2022
32022
Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
YJ Kim, R Fahim, HH Awadalla
arXiv preprint arXiv:2310.02410, 2023
22023
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20