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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Koopman Operator learning for Accelerating Quantum Optimization and Machine Learning


Nov 02, 2022
Di Luo, Jiayu Shen, Rumen Dangovski, Marin Soljačić

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

On the Importance of Calibration in Semi-supervised Learning


Oct 10, 2022
Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj, Seungwook Han, Ligong Han, Leonid Karlinsky, Marin Soljacic, Akash Srivastava

Add code

* 24 pages 

   Access Paper or Ask Questions

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

AI-Assisted Discovery of Quantitative and Formal Models in Social Science


Oct 02, 2022
Julia Balla, Sihao Huang, Owen Dugan, Rumen Dangovski, Marin Soljacic

Add code

* 19 pages, 4 figures 

   Access Paper or Ask Questions

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

Discovering Conservation Laws using Optimal Transport and Manifold Learning


Aug 31, 2022
Peter Y. Lu, Rumen Dangovski, Marin Soljačić

Add code

* 16 pages, 11 figures (7 main text, 4 supplemental), 1 table (supplemental) 

   Access Paper or Ask Questions

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

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings


Apr 21, 2022
Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljačić, Shang-Wen Li, Wen-tau Yih, Yoon Kim, James Glass

Add code

* NAACL 2022 main conference (Long paper). Pretrained models and code are available at https://github.com/voidism/DiffCSE 

   Access Paper or Ask Questions

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

Meta-Learning and Self-Supervised Pretraining for Real World Image Translation


Dec 22, 2021
Ileana Rugina, Rumen Dangovski, Mark Veillette, Pooya Khorrami, Brian Cheung, Olga Simek, Marin Soljačić

Add code

* 10 pages, 8 figures, 2 tables 

   Access Paper or Ask Questions

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

Equivariant Contrastive Learning


Oct 28, 2021
Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljačić

Add code

* 17 pages, 5 figures 

   Access Paper or Ask Questions

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

Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science


Oct 15, 2021
Charlotte Loh, Thomas Christensen, Rumen Dangovski, Samuel Kim, Marin Soljacic

Add code

* 21 pages, 10 figures 

   Access Paper or Ask Questions

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

Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks


Nov 20, 2020
Ileana Rugina, Rumen Dangovski, Li Jing, Preslav Nakov, Marin Soljačić

Add code

* 9 pages, 6 figures, 9 tables 

   Access Paper or Ask Questions

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

Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications


Oct 06, 2020
Matthew Khoury, Rumen Dangovski, Longwu Ou, Preslav Nakov, Yichen Shen, Li Jing

Add code

* To appear at the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP '20), November 16-20, 2020, NMT, AI accelerators, co-design, TPU, OPU, 10 pages, 3 figures, 4 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>