Daniel Duckworth
Daniel Duckworth
Verified email at google.com - Homepage
Cited by
Cited by
Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations
J Van Den Berg, S Miller, D Duckworth, H Hu, A Wan, XY Fu, K Goldberg, ...
2010 IEEE International Conference on Robotics and Automation, 2074-2081, 2010
Nerf in the wild: Neural radiance fields for unconstrained photo collections
R Martin-Brualla, N Radwan, MSM Sajjadi, JT Barron, A Dosovitskiy, ...
arXiv preprint arXiv:2008.02268, 2020
Taskmaster-1: Toward a realistic and diverse dialog dataset
B Byrne, K Krishnamoorthi, C Sankar, A Neelakantan, D Duckworth, ...
arXiv preprint arXiv:1909.05358, 2019
The importance of generation order in language modeling
N Ford, D Duckworth, M Norouzi, GE Dahl
arXiv preprint arXiv:1808.07910, 2018
Automatic detection of generated text is easiest when humans are fooled
D Ippolito, D Duckworth, C Callison-Burch, D Eck
arXiv preprint arXiv:1911.00650, 2019
Invertible convolutional flow
M Karami, D Schuurmans, J Sohl-Dickstein, L Dinh, D Duckworth
Human and automatic detection of generated text
D Ippolito, D Duckworth, C Callison-Burch, D Eck
arXiv preprint arXiv:1911.00650, 2019
Monte carlo methods for multiple target tracking and parameter estimation
D Duckworth
Master’s thesis, EECS Department, University of California, Berkeley, 2012
Trading off diversity and quality in natural language generation
H Zhang, D Duckworth, D Ippolito, A Neelakantan
arXiv preprint arXiv:2004.10450, 2020
Neural assistant: Joint action prediction, response generation, and latent knowledge reasoning
A Neelakantan, S Yavuz, S Narang, V Prasad, B Goodrich, D Duckworth, ...
arXiv preprint arXiv:1910.14613, 2019
Parallel scheduled sampling
D Duckworth, A Neelakantan, B Goodrich, L Kaiser, S Bengio
arXiv preprint arXiv:1906.04331, 2019
ScalaNLP: Breeze
D Hall, D Ramage, J Zaugg, A Lehmann, J Merritt, K Stevens, J Baldridge, ...
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
NS Wadia, D Duckworth, SS Schoenholz, E Dyer, J Sohl-Dickstein
arXiv preprint arXiv:2008.07545, 2020
Stochastic natural gradient descent draws posterior samples in function space
SL Smith, D Duckworth, S Rezchikov, QV Le, J Sohl-Dickstein
arXiv preprint arXiv:1806.09597, 2018
Generative convolutional flow for density estimation
M Karami, L Dinh, D Duckworth, J Sohl-Dickstein, D Schuurmans
Workshop on Bayesian Deep Learning NeurIPS 2018, 2018
Predicting a search engine ranking signal value
JS Arrizabalaga, M Nuhn, QV Le, D Duckworth, M Heiler
US Patent 10,324,993, 2019
Generating automated assistant responses and/or actions directly from dialog history and resources
A Neelakantan, D Duckworth, B Goodrich, V Prasad, C Sankar, S Yavuz
US Patent App. 16/910,435, 2020
The Importance of Generation Order in Language Modeling
D Duckworth, G Dahl, M Norouzi, N Ford
The system can't perform the operation now. Try again later.
Articles 1–18