avatar

Yimeng Wu

NLP Researcher
Huawei Noah's Ark Lab, Hong Kong
yimengwu71@gmail.com


About Me

I am currently an NLP researcher at Huawei Noah’s Ark Lab in Hong Kong SAR. Before this, I worked at Huawei Canada Research Centre for 3 years. My work involves building pre-trained models for customers and conducting research related to model compression.

I completed my Master’s degree in Electrical and Computer Engineering from McGill University in 2019, under the supervision of Dr. Ioannis Psaromiligkos. I received my Bachelor’s degree in Biomedical Engineering from Tianjin University in 2017.

Always looking for research interns who are interested in LLMs, especially MoE pretraining. Feel free to shoot me an email. For more details please check here.

Research Interests

News

Selected Publications

  1. NAACL
    Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
    Marzieh Tahaei, Aref Jafari, Ahmad Rashid, David Alfonso-Hermelo, Khalil Bibi, Yimeng Wu, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
    Findings of the Association for Computational Linguistics (NAACL), 2024.
    PDF BibTex

  2. ACL
    AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
    Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
    Findings of the Association for Computational Linguistics (ACL), 2023.
    PDF BibTex

  3. EMNLP
    Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing
    Abbas Ghaddar*, Yimeng Wu*, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais (*Equal Contribution)
    Empirical Methods in Natural Language Processing (EMNLP), 2022.
    PDF Project Page BibTex

  4. EMNLP
    Universal-KD: Attention-based output-grounded intermediate layer knowledge distillation
    Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md Akmal Haidar, Ali Ghodsi
    Empirical Methods in Natural Language Processing (EMNLP), 2021.
    PDF BibTex Oral Presentation

  5. AAAI
    Alp-kd: Attention-based layer projection for knowledge distillation
    Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh, Qun Liu
    Association for the Advancement of Artificial Intelligence (AAAI), 2021.
    PDF BibTex

  6. ArXiv
    JABER and SABER: Junior and Senior Arabic BERt
    Abbas Ghaddar, Yimeng Wu, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Duan Xinyu, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Philippe Langlais
    Preprint, 2021.
    PDF Code Project Page BibTex

  7. EMNLP
    Why skip if you can combine: A simple knowledge distillation technique for intermediate layers
    Yimeng Wu*, Peyman Passban*, Mehdi Rezagholizade, Qun Liu (*Equal Contribution)
    Empirical Methods in Natural Language Processing (EMNLP), 2020.
    PDF Code BibTex

Services

Conference Reviewers


Powered by Jekyll and Minimal Light theme.