Architecture researcherTraining-method researcher
Quoc V. Le
Also published as Quoc Le.
Contributed across Google language-model work spanning sequence-to-sequence learning and instruction finetuning that let models follow tasks zero-shot.
Works in the archive (7)
- Sequence to Sequence Learning with Neural Networks · 2014
- Outrageously Large Neural Networks: Sparsely-Gated MoE · 2017
- Self-Attention with Relative Position Representations / Transformer-XL · 2018
- ELECTRA: Pre-training Text Encoders as Discriminators · 2020
- Finetuned Language Models Are Zero-Shot Learners (FLAN) / Self-Instruct · 2022
- Chain-of-Thought Prompting Elicits Reasoning · 2022
- Structured Reasoning: Least-to-Most / PoT / Tree of Thoughts · 2023
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.
Co-authors in the archive
View co-author network (25 people)
Loading graph…