VIDEO DOI: https://doi.org/10.48448/8q0r-kr59

technical paper

EMNLP 2021

November 08, 2021

Live on Underline

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

Please log in to leave a comment

Downloads

SlidesPaperTranscript English (automatic)

Next from EMNLP 2021

MATE: Multi-view Attention for Table Transformer Efficiency
technical paper

MATE: Multi-view Attention for Table Transformer Efficiency

EMNLP 2021

+1Maharshi GorWilliam W. CohenJulian Eisenschlos
Julian Eisenschlos and 3 other authors

08 November 2021

Similar lecture

The Power of Scale for Parameter-Efficient Prompt Tuning
poster

The Power of Scale for Parameter-Efficient Prompt Tuning

EMNLP 2021

Noah ConstantBrian Lester
Brian Lester and 2 other authors

08 November 2021

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved