Architecture researcher
Noah A. Smith
Co-authored ALiBi position biasing, letting transformers extrapolate to sequences longer than those seen in training.
Works in the archive (2)
- Train Short Test Long: Attention with Linear Biases (ALiBi) · 2021
- Finetuned Language Models Are Zero-Shot Learners (FLAN) / Self-Instruct · 2022
“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 (9 people)
Loading graph…