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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models


Jun 30, 2022
Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, Ruslan Salakhutdinov

* Code available at: https://github.com/pliang279/MultiViz. arXiv admin note: substantial text overlap with arXiv:2107.07502 

   Access Paper or Ask Questions

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

DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations


Mar 03, 2022
Yiwei Lyu, Paul Pu Liang, Zihao Deng, Ruslan Salakhutdinov, Louis-Philippe Morency

* Code available at https://github.com/lvyiwei1/DIME 

   Access Paper or Ask Questions

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

Provable Hierarchical Lifelong Learning with a Sketch-based Modular Architecture


Dec 21, 2021
Zihao Deng, Zee Fryer, Brendan Juba, Rina Panigrahy, Xin Wang


   Access Paper or Ask Questions

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

Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization


Nov 17, 2021
Hmrishav Bandyopadhyay, Zihao Deng, Leiting Ding, Sinuo Liu, Mostofa Rafid Uddin, Xiangrui Zeng, Sima Behpour, Min Xu

* Bioinformatics 2021 
* 14 pages 

   Access Paper or Ask Questions

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

Variability-Aware Training and Self-Tuning of Highly Quantized DNNs for Analog PIM


Nov 11, 2021
Zihao Deng, Michael Orshansky

* This is the preprint version of our paper accepted in DATE 2022 

   Access Paper or Ask Questions

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

Polynomial Time Reinforcement Learning in Correlated FMDPs with Linear Value Functions


Jul 12, 2021
Siddartha Devic, Zihao Deng, Brendan Juba

* 30 pages, 1 figure 

   Access Paper or Ask Questions

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

Training with Multi-Layer Embeddings for Model Reduction


Jun 10, 2020
Benjamin Ghaemmaghami, Zihao Deng, Benjamin Cho, Leo Orshansky, Ashish Kumar Singh, Mattan Erez, Michael Orshansky

* 10 pages, 3 figures 

   Access Paper or Ask Questions

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