April 26, 2020
State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make output predictions at different stages of the network and we investigate different ways to predict how much computation is required for a particular sequence. Unlike dynamic computation in Universal Transformers, which applies the same set of layers iteratively, we apply different layers at every step to adjust both the amount of computation as well as the model capacity. On IWSLT German-English translation our approach matches the accuracy of a well tuned baseline Transformer while using less than a quarter of the decoder layers.
Publisher
International Conference on Learning Representations (ICLR)
Research Topics
April 25, 2025
Rulin Shao, Qiao Rui, Varsha Kishore, Niklas Muennighoff, Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Scott Yih, Pang Wei Koh, Luke Zettlemoyer
April 25, 2025
April 17, 2025
Ansong Ni, Ruta Desai, Yang Li, Xinjie Lei, Dong Wang, Ramya Raghavendra, Gargi Ghosh, Daniel Li (FAIR), Asli Celikyilmaz
April 17, 2025
March 17, 2025
Zhaofeng Wu, Michihiro Yasunaga, Andrew Cohen, Yoon Kim, Asli Celikyilmaz, Marjan Ghazvininejad
March 17, 2025
February 06, 2025
Jarod Levy, Mingfang (Lucy) Zhang, Svetlana Pinet, Jérémy Rapin, Hubert Jacob Banville, Stéphane d'Ascoli, Jean Remi King
February 06, 2025
April 30, 2018
Yedid Hoshen, Lior Wolf
April 30, 2018
November 01, 2018
Yedid Hoshen, Lior Wolf
November 01, 2018
December 02, 2018
Sagie Benaim, Lior Wolf
December 02, 2018
June 30, 2019
Geng Ji, Dehua Cheng, Huazhong Ning, Changhe Yuan, Hanning Zhou, Liang Xiong, Erik B. Sudderth
June 30, 2019
Our approach
Latest news
Foundational models