🧑‍🔬 Andrew Dai

🏛️ Affiliations

🏢GoogleMountain View · United States2015–2023 · 12 papers🎓University of EdinburghEdinburgh · United Kingdom2009–2011 · 3 papers

🏛️Aleph Alpha GmbHHeidelberg · Germany2022–2024Employment 2022–2024 · Researcher

🏢Sakana AITokyo · Japan2024Employment since 2024🎓Trinity College DublinDublin · Ireland2016–2021Education 2016–2021 · Masters in Mechanical and Manufacturing Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Generating Sentences from a Continuous Space (2016 · 2,435 citations)
   The paper tackles a limitation of the standard rnnlm. It builds text one token after another and never forms one explicit vector for the whole sentence, so properties like topic, style or overall syntax stay hidden. The authors adapt the variational autoencoder to sentences. A single-layer LSTM encoder maps a…
2. Quality-Diversity through AI Feedback (2023 · 19 citations)
   Quality-diversity (QD) search maintains a population of solutions that are both good and varied. However, it has rarely been used for creative text because quality and diversity are hard to define in code. The authors propose QDAIF, an evolutionary method in which language models handle all three parts of QD search.…

All works

13 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Scaling Instruction-Finetuned Language Models ↗arXiv:2210.11416 · no summary yetHyung Won Chung et al.2022 · 3,392 citations
2. Generating Sentences from a Continuous SpaceConference on Computational Natural Language Learning (CoNLL)Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, et al.2016 · 2,435 citations
3. Semi-supervised Sequence Learning ↗arXiv (Cornell University) · no summary yetAndrew M. Dai, Quoc Viet Le2015 · 723 citations
4. Document Embedding with Paragraph Vectors ↗arXiv (Cornell University) · no summary yetAndrew M. Dai, Christopher Olah, Quoc Viet Le2015 · 272 citations
5. Music Transformer ↗arXiv (Cornell University) · no summary yetCheng-Zhi Anna Huang et al.2018 · 117 citations
6. Learning Longer-term Dependencies in RNNs with Auxiliary Losses ↗arXiv (Cornell University) · no summary yetTrieu H. Trinh et al.2018 · 104 citations
7. Training Socially Aligned Language Models on Simulated Social Interactions ↗arXiv:2305.16960 · no summary yetRuibo Liu et al.2023 · 94 citations
8. Gmail Smart Compose: Real-Time Assisted Writing ↗arXiv (Cornell University) · no summary yetMia Xu Chen et al.2019 · 89 citations
9. Quality-Diversity through AI FeedbackarXiv:2310.13032Herbie Bradley, Andrew Dai, Hannah Teufel, et al.2023 · 19 citations
10. Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models ↗arXiv:2412.02980 · no summary yetAlex Havrilla et al.2024 · 17 citations
11. Compositionality and Capacity in Emergent Languages ↗Proceedings of the 5th Workshop on Representation Learning for NLP · no summary yetAbhinav Gupta et al.2020 · 8 citations
12. Brainformers: Trading Simplicity for Efficiency ↗arXiv (Cornell University) · no summary yetYanqi Zhou et al.2023 · 6 citations
13. A Goal-oriented Neural Conversation Model by Self-Play ↗no summary yetWei Wei et al.2018 · 3 citations

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Hannah Teufel
• Herbie Bradley
• Jeff Clune
• Luke Vilnis
• Marco Bellagente
• Oriol Vinyals
• Rafal Jozefowicz
• Samuel R. Bowman
• Samy Bengio

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Computational Natural Language Learning (CoNLL): CoNLL 2016
• Transactions of the Association for Computational Linguistics (TACL)
• Proceedings of the 5th Workshop on Representation Learning for NLP

🔗 Cited by

Papers of our library cite their works 15,878 times (of the 149,439 papers whose bibliographies we read); 2,333 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/andrew-dai/