Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
January 2024
Young Jin Kim
Principal Researcher, Microsoft GenAI
Publications
Publications by Year
-
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
ICML 2024 | January 2024
-
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2023
Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
Young Jin Kim, Raffy Fahim, Hany Hassan Awadalla
December 2023
Task-Based MoE for Multitask Multilingual Machine Translation
Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P Woodruff, Barnabas Poczos, Hany Hassan Awadalla
December 2023
PEMA: Plug-in External Memory Adaptation for Language Models
HyunJin Kim, Young Jin Kim, JinYeong Bak
November 2023
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
Haoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan Awadalla
Accepted to ICLR 2024 | September 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks Lakshmanan, V.S., Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL 2023 | June 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla
February 2023
-
Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2022
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU
Hossam Amer, Young Jin Kim, Mohamed Afify, Hitokazu Matsushita, Hany Hassan Awadalla
AMTA | August 2022
Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
Rui Liu, Young Jin Kim, Alexandre Muzio, Hany Hassan Awadalla
ICML 2022 | July 2022
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan Awadalla, Ruofei Zhang, Tuo Zhao, Jianfeng Gao
ICLR 2022 | April 2022
-
Taming Sparsely Activated Transformer with Stochastic Experts.
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao, Hany Hassan Awadalla
October 2021
Scalable and Efficient MoE Training for Multitask Multilingual Models
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio, Felipe Cruz Salinas, Liyang Lu, Amr Hendy, Samyam Rajbhandari, Yuxiong He, Hany Hassan Awadalla
September 2021
-
FastFormers: Highly Efficient Transformer Models for Natural Language Understanding
Young Jin Kim, Hany Hassan Awadalla
SustaiNLP - EMNLP | November 2020
-
Time- and space-parallel simulation of air traffic networks
Young Jin Kim, Dimitri Mavris, Richard Fujimoto
SIMULATION (SAGE) | December 2019, Vol 95(12): pp. 1213-1228
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
Publications by Research Area
-
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
January 2024
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
ICML 2024 | January 2024
Task-Based MoE for Multitask Multilingual Machine Translation
Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P Woodruff, Barnabas Poczos, Hany Hassan Awadalla
December 2023
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2023
Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
Young Jin Kim, Raffy Fahim, Hany Hassan Awadalla
December 2023
PEMA: Plug-in External Memory Adaptation for Language Models
HyunJin Kim, Young Jin Kim, JinYeong Bak
November 2023
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
Haoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan Awadalla
Accepted to ICLR 2024 | September 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks Lakshmanan, V.S., Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL 2023 | June 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla
February 2023
Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2022
Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
Rui Liu, Young Jin Kim, Alexandre Muzio, Hany Hassan Awadalla
ICML 2022 | July 2022
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan Awadalla, Ruofei Zhang, Tuo Zhao, Jianfeng Gao
ICLR 2022 | April 2022
Taming Sparsely Activated Transformer with Stochastic Experts.
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao, Hany Hassan Awadalla
October 2021
Scalable and Efficient MoE Training for Multitask Multilingual Models
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio, Felipe Cruz Salinas, Liyang Lu, Amr Hendy, Samyam Rajbhandari, Yuxiong He, Hany Hassan Awadalla
September 2021
FastFormers: Highly Efficient Transformer Models for Natural Language Understanding
Young Jin Kim, Hany Hassan Awadalla
SustaiNLP - EMNLP | November 2020
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
-
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU
Hossam Amer, Young Jin Kim, Mohamed Afify, Hitokazu Matsushita, Hany Hassan Awadalla
AMTA | August 2022
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan Awadalla, Ruofei Zhang, Tuo Zhao, Jianfeng Gao
ICLR 2022 | April 2022
Taming Sparsely Activated Transformer with Stochastic Experts.
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao, Hany Hassan Awadalla
October 2021
Scalable and Efficient MoE Training for Multitask Multilingual Models
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio, Felipe Cruz Salinas, Liyang Lu, Amr Hendy, Samyam Rajbhandari, Yuxiong He, Hany Hassan Awadalla
September 2021
FastFormers: Highly Efficient Transformer Models for Natural Language Understanding
Young Jin Kim, Hany Hassan Awadalla
SustaiNLP - EMNLP | November 2020
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
-
Time- and space-parallel simulation of air traffic networks
Young Jin Kim, Dimitri Mavris, Richard Fujimoto
SIMULATION (SAGE) | December 2019, Vol 95(12): pp. 1213-1228
Publications by Type
-
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
ICML 2024 | January 2024
Task-Based MoE for Multitask Multilingual Machine Translation
Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P Woodruff, Barnabas Poczos, Hany Hassan Awadalla
December 2023
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
Haoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan Awadalla
Accepted to ICLR 2024 | September 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks Lakshmanan, V.S., Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL 2023 | June 2023
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers
Ganesh Jawahar, Subhabrata (Subho) Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Awadallah, Sébastien Bubeck, Jianfeng Gao
ACL | May 2023
Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2022
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU
Hossam Amer, Young Jin Kim, Mohamed Afify, Hitokazu Matsushita, Hany Hassan Awadalla
AMTA | August 2022
Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
Rui Liu, Young Jin Kim, Alexandre Muzio, Hany Hassan Awadalla
ICML 2022 | July 2022
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan Awadalla, Ruofei Zhang, Tuo Zhao, Jianfeng Gao
ICLR 2022 | April 2022
Taming Sparsely Activated Transformer with Stochastic Experts.
Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao, Hany Hassan Awadalla
October 2021
FastFormers: Highly Efficient Transformer Models for Natural Language Understanding
Young Jin Kim, Hany Hassan Awadalla
SustaiNLP - EMNLP | November 2020
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan Awadalla, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
WNGT - EMNLP | November 2019
-
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, Young Jin Kim
January 2024
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
Young Jin Kim, Rawn Henry, Raffy Fahim, Hany Hassan Awadalla
December 2023
Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
Young Jin Kim, Raffy Fahim, Hany Hassan Awadalla
December 2023
PEMA: Plug-in External Memory Adaptation for Language Models
HyunJin Kim, Young Jin Kim, JinYeong Bak
November 2023
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla
February 2023
Scalable and Efficient MoE Training for Multitask Multilingual Models
Young Jin Kim, Ammar Ahmad Awan, Alexandre Muzio, Felipe Cruz Salinas, Liyang Lu, Amr Hendy, Samyam Rajbhandari, Yuxiong He, Hany Hassan Awadalla
September 2021
-
Time- and space-parallel simulation of air traffic networks
Young Jin Kim, Dimitri Mavris, Richard Fujimoto
SIMULATION (SAGE) | December 2019, Vol 95(12): pp. 1213-1228