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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Representing Long-Range Context for Graph Neural Networks with Global Attention


Jan 21, 2022
Zhanghao Wu, Paras Jain, Matthew A. Wright, Azalia Mirhoseini, Joseph E. Gonzalez, Ion Stoica

Add code

* NeurIPS 2021. The first two authors contributed equally to this work 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines


Jun 02, 2021
Matthew A. Wright, Joseph E. Gonzalez

Add code

* Work in progress, comments welcome 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models


Apr 21, 2021
Nicholas Rhinehart, Jeff He, Charles Packer, Matthew A. Wright, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine

Add code

* To be published at ICRA 2021. Project page: https://sites.google.com/view/contingency-planning 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles


Apr 16, 2021
Ionel Gog, Sukrit Kalra, Peter Schafhalter, Matthew A. Wright, Joseph E. Gonzalez, Ion Stoica

Add code

* ICRA 2021; 8 pages, 4 figures, 1 table 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning


May 31, 2019
Matthew A. Wright, Roberto Horowitz

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs


Apr 23, 2019
Matthew A. Wright, Simon F. G. Ehlers, Roberto Horowitz

Add code

* Submitted to 2019 IEEE Conference on Intelligent Transportation Systems 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email