no code implementations • 5 Oct 2023 • Litton J Kurisinkel, Nancy F Chen
Memory-efficient large language models are good at refining text input for better readability.
no code implementations • NAACL 2021 • Litton J Kurisinkel, Ai Ti Aw, Nancy F Chen
Neural models for text generation are often designed in an end-to-end fashion, typically with zero control over intermediate computations, limiting their practical usability in downstream applications.