Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Charles Sutton

Charles Sutton

A Library for Representing Python Programs as Graphs for Machine Learning

Aug 15, 2022
David Bieber, Kensen Shi, Petros Maniatis, Charles Sutton, Vincent Hellendoorn, Daniel Johnson, Daniel Tarlow

Figure 1 for A Library for Representing Python Programs as Graphs for Machine Learning

Figure 2 for A Library for Representing Python Programs as Graphs for Machine Learning

Figure 3 for A Library for Representing Python Programs as Graphs for Machine Learning

Figure 4 for A Library for Representing Python Programs as Graphs for Machine Learning

* 21 pages, 14 figures

Access Paper or Ask Questions

Language Model Cascades

Jul 28, 2022
David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

Figure 1 for Language Model Cascades

Figure 2 for Language Model Cascades

Figure 3 for Language Model Cascades

Figure 4 for Language Model Cascades

* Presented as spotlight at the Beyond Bases workshop at ICML 2022 (https://beyond-bayes.github.io)

Access Paper or Ask Questions

Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Jul 17, 2022
Simao Eduardo, Kai Xu, Alfredo Nazabal, Charles Sutton

Figure 1 for Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Figure 2 for Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Figure 3 for Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Figure 4 for Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

* Submitted for review in ICLR 2022

Access Paper or Ask Questions

PaLM: Scaling Language Modeling with Pathways

Apr 19, 2022
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov, Noah Fiedel

Figure 1 for PaLM: Scaling Language Modeling with Pathways

Figure 2 for PaLM: Scaling Language Modeling with Pathways

Figure 3 for PaLM: Scaling Language Modeling with Pathways

Figure 4 for PaLM: Scaling Language Modeling with Pathways

Access Paper or Ask Questions

Compositional Generalization and Decomposition in Neural Program Synthesis

Apr 07, 2022
Kensen Shi, Joey Hong, Manzil Zaheer, Pengcheng Yin, Charles Sutton

Figure 1 for Compositional Generalization and Decomposition in Neural Program Synthesis

Figure 2 for Compositional Generalization and Decomposition in Neural Program Synthesis

Figure 3 for Compositional Generalization and Decomposition in Neural Program Synthesis

Figure 4 for Compositional Generalization and Decomposition in Neural Program Synthesis

* Published at the Deep Learning for Code (DL4C) Workshop at ICLR 2022

Access Paper or Ask Questions

CrossBeam: Learning to Search in Bottom-Up Program Synthesis

Mar 20, 2022
Kensen Shi, Hanjun Dai, Kevin Ellis, Charles Sutton

Figure 1 for CrossBeam: Learning to Search in Bottom-Up Program Synthesis

Figure 2 for CrossBeam: Learning to Search in Bottom-Up Program Synthesis

Figure 3 for CrossBeam: Learning to Search in Bottom-Up Program Synthesis

Figure 4 for CrossBeam: Learning to Search in Bottom-Up Program Synthesis

* Published at ICLR 2022

Access Paper or Ask Questions