Cite
Notes
Only stored in your browser.
Attribution
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
arXiv 2024
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
from 2 papers
J. Zico Kolter
Albert Gu
Aviv Bick
Eric P. Xing
Joao D. Semedo
Sachin Goyal