Michiel de Jong

Researcher, Augment Computing

Joined

September 2021

Names

Michiel de Jong (Preferred)

Emails

****@gmail.com (Confirmed)

****@google.com (Confirmed)

****@usc.edu (Confirmed)

****@augmentcode.com (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Researcher

Augment Computing (augmentcode.com)

2023 – Present

PhD student

University of Southern California (usc.edu)

2018 – 2023

Advisors, Relations & Conflicts

Coauthor

William Cohen

2021 – Present

Coauthor

Nicholas FitzGerald

2021 – Present

PhD Advisor

Fei Sha

2018 – Present

Coauthor

Yury Zemlyanskiy

2018 – Present

Expertise

No areas of expertise listed

Publications

GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebron, Sumit Sanghai
- EMNLP 2023 Main
- Readers: Everyone
CoLT5: Faster Long-Range Transformers with Conditional Computation
Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontanon, Siddhartha Brahma, Yury Zemlyanskiy, David Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai
- EMNLP 2023 Main
- Readers: Everyone
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Joshua Ainslie, Sumit Sanghai, Fei Sha, William W. Cohen
- ICML 2023 Poster
- Readers: Everyone
CoLT5: Faster Long-Range Transformers with Conditional Computation
Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontañón, Siddhartha Brahma, Yury Zemlyanskiy, David C. Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai
- 2023 (modified: 28 Mar 2023)
- CoRR 2023
- Readers: Everyone
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Joshua Ainslie, Sumit Sanghai, Fei Sha, William Cohen
- 2023 (modified: 28 Mar 2023)
- CoRR 2023
- Readers: Everyone
QA Is the New KR: Question-Answer Pairs as Knowledge Bases
William W. Cohen, Wenhu Chen, Michiel de Jong, Nitish Gupta, Alessandro Presta, Pat Verga, John Wieting
- Published: 01 Jan 2023, Last Modified: 07 Oct 2023
- AAAI 2023
- Readers: Everyone
Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
Wenhu Chen, Pat Verga, Michiel de Jong, John Wieting, William W. Cohen
- Published: 01 Jan 2023, Last Modified: 07 Oct 2023
- EACL 2023
- Readers: Everyone
CoLT5: Faster Long-Range Transformers with Conditional Computation
Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontañón, Siddhartha Brahma, Yury Zemlyanskiy, David C. Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai
- Published: 01 Jan 2023, Last Modified: 17 Dec 2023
- EMNLP 2023
- Readers: Everyone
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebrón, Sumit Sanghai
- Published: 01 Jan 2023, Last Modified: 17 Dec 2023
- EMNLP 2023
- Readers: Everyone
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference
Michiel de Jong, Yury Zemlyanskiy, Joshua Ainslie, Nicholas FitzGerald, Sumit Sanghai, Fei Sha, William W. Cohen
- Published: 01 Jan 2023, Last Modified: 17 Dec 2023
- ACL (Findings) 2023
- Readers: Everyone

View all 32 publications

Co-Authors

View all 52 co-authors