Nate Kushman
Senior Research Scientist
DeepMind
6 Pancras Square
London, UK
nate at kushman DOT org
|
|
|
Publications
- Competition-Level Code Generation with AlphaCode
Yujia Li*
, David Choi*
, Junyoung Chung*
, Nate Kushman*
, Julian Schrittwieser*
, Rémi Leblond*
, Tom
Eccles*
, James Keeling*
, Felix Gimeno*
, Agustin Dal Lago*
, Thomas Hubert*
, Peter Choy*
, Cyprien de
Masson d’Autume*
, Igor Babuschkin, Xinyun Chen, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey
Cherepanov, James Molloy, Daniel J. Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de
Freitas, Koray Kavukcuoglu, Oriol Vinyals
- Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
Sebastian Lunz, Yingzhen Li, Andrew Fitzgibbon, Nate Kushman
Appeared at NeurIPS 2020 Workshop on Differentiable vision, graphics, and physics applied to machine learning
- Interpreting Spatially Infinite Generative Models
Chaochao Lu, Richard E. Turner, Yingzhen Li, Nate Kushman
Appeared at ICML 2020 Workshop on Human Interpretability (WHI)
- Learning Robust Representations via Multi-View Information Bottleneck
Marco Federici, Anjan Dutta, Patrick Forré, Nate Kushman, Zeynep Akata
Appeared at ICLR 2020
- Inverting Supervised Representations with Autoregressive Neural Density Models
Charlie Nash, Nate Kushman, Christopher K. I. Williams
Appeared at AISTATS 2019
- Constructing Unrestricted Adversarial Examples with Generative Models
Yang Song, Rui Shu, Nate Kushman, Stefano Ermon
Appeared at NeurIPS 2018
- Understanding the Rational Speech Act Model
Arianna Yuan, Will Monroe, Yu Bai, Nate Kushman
Appeared at CogSci 2018
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman
Appeared at ICLR 2018
- Generative Entity Networks: Disentangling Entities and Attributes in Visual Scenes using Partial Natural Language Descriptions
Charlie Nash, Sebastian Nowozin, Nate Kushman
- The Mutual AutoEncoder: Controlling Information in Latent Code Representations
Bui Thi Mai Phuong, Max Welling, Nate Kushman, Ryota Tomioka, Sebastian Nowozin
- Differentiable Programs with Neural Libraries
Alexander L Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
Appeared at ICML 2017
- A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
-
Felix Leibfried, Nate Kushman, Katja Hofmann
Appeared at ICML Workshop on Principled Approaches to Deep Learning (PADL) 2017
- Neural Program Lattices
Chengtao Li, Daniel Tarlow, Alex Gaunt, Marc Brockschmidt, Nate Kushman
Appeared at ICLR 2017
- Lifelong Perceptual Programming By Example
Alexander L Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
Appeared at ICLR Workshop 2017
- Terpret: A probabilistic programming language for program induction
Alexander L Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, and Daniel Tarlow
Short version appeared at NIPS Workshop on Neural Abstract Machines and Program Induction (NAMPI) 2016
Best Paper Award
- Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
Nicholas Locascio, Karthik Narasimhan, Eduardo DeLeon, Nate Kushman, and Regina Barzilay
Appeared at EMNLP 2016
- MAWPS: A Math Word Problem Repository
Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, and Hannaneh Hajishirzi
Appeared at NAACL 2016
- Generating Computer Programs from Natural Language Descriptions
Nate Kushman
PhD Thesis, 2015
- Learning to Automatically Solve Algebra Word Problems
Nate Kushman, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay
Appeared at ACL 2014
PDF
Slides
Code and Data
PRESS: MIT (Frontpage) Technology Review HackerNews (Frontpage) Others: [1][2]
-
Learning to Solve Arithmetic Word Problems with Verb Categorization
Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman
Appeared at EMNLP 2014
PDF
Code
and Data
-
Using Semantic Unification to Generate Regular Expressions from Natural Language
Nate Kushman and Regina Barzilay
Appeared at NAACL 2013
PDF
Slides
Code and Data
PRESS: MIT (Frontpage) GigaOm Others: [1][2][3][4][5]
-
Learning High-Level Planning from Text
S.R.K. Branavan, Nate Kushman, Tao Lei and Regina Barzilay
Appeared at ACL 2012
PDF
Slides
Code and Data
-
ZipTx: Harnessing Partial Packets in 802.11 Networks
Kate Ching-Ju Lin*, Nate Kushman* and Dina Katabi
Appeared at Mobicom 2008
PDF,
Slides
*equal contribution
-
Learning to Share: Narrowband-Friendly Wideband Networks.
Hariharan Rahul, Nate Kushman, Dina Katabi, Charles Sodini, and Farinaz Edalat
Appeared at SIGCOMM 2008
PDF
-
R-BGP: Staying Connected In a Connected World
Nate Kushman, Srikanth Kandula, Dina Katabi, and Bruce M. Maggs
Appeared at NSDI 2007
PDF,
Tech Report with full proofs (PDF),
NSDI Slides,
Nanog Slides
-
Can You Hear Me Now?! It Must be BGP.
Nate Kushman, Srikanth Kandula, Dina Katabi
Appeared in CCR 2007
PDF
-
Performance Nonmonotonicities: A Case Study of the UltraSPARC Processor
Master's Thesis
PDF
|
|
|
