Cite
Notes
Only stored in your browser.
Attribution
Repeat After Me: Transformers are Better than State Space Models at Copying
arXiv 2024
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Eliminating Position Bias of Language Models: A Mechanistic Approach
from 3 papers
Aditya Kusupati
Alan Fan
Ali Farhadi
CEO
Ari Holtzman
Chi Han
David Brandfonbrener
Eran Malach
Ethan Shen
HANLIN ZHANG
Hao Peng