Transformers Can Compose Skills To Solve Novel Problems Without Finetuning

Samuel R. Bowman, Gabor Angeli, Christopher Potts, Tom B. Brown, Benjamin Mann, Nick Ryder, Jared D Subbiah, Prafulla Kaplan, A. Dhariwal, Gretchen Krueger, T. Henighan, R. Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom, Kwiatkowski Michael, Collins Kristina, Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Tushar Daniel Khashabi, Tomás Kociský, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz, Gábor Melis, Guokun Lai, Qi Xie, Hanxiao Liu, Yiming Yang, Jennifer Dy, Andreas Krause, Mike Lewis, Yinhan Liu, Marjan Naman Goyal, Abdelrahman Ghazvininejad, Omer Mohamed, Levy, Patrick Lewis, Pontus Stenetorp, Sebastian Riedel, Kevin Lin, Oyvind Tafjord, Christopher D. Manning, Kevin Clark, John Hewitt, Todor Mihaylov, Colin Raffel, Noam M. Shazeer, A. Roberts, Sharan Lee, Michael Narang, Yanqi Matena, Wei Zhou, Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Networks. In, Matthew Richardson, C. Burges

Author Locations

No location data available for the ELLIS authors of this paper.

ELLIS Edge Newsletter
Join the 6,000+ people who get the monthly newsletter filled with the latest news, jobs, events and insights from the ELLIS Network.