sandeep@mila
:
~
$
 cat sandeep.txt

********
About Me
********

Hi, I'm 
Sandeep Subramanian
, a 
PhD student
 
at MILA (Université de Montréal). 

I'm advised by Chris Pal and Yoshua Bengio.

At present, I'm interested in building,
understanding and manipulating distributed
representations of text.

       What        is       the   singularity?
         |         |         |         |      
       (   )―――――(   )―――――(   )―――――(   )―――――
                                              |
     ------------------------------------------
     |
      -(   )―――――(   )―――――(   )―――――(   )
         |         |         |         |
        The     optimal     1x1   convolution 


Previously, I was a 
masters student
 at 
Carnegie Mellon Unviersity.

****
News
****

[
1
] Our paper on training 
generative models for text
 by 
    modeling the distribution of general purpose sentence            
    encoders has been accepted at 
NIPS 2018! 
[
2
] I worked on text-rewriting during my internship  
    at 
Facebook AI Research, New York
 this summer 
    with Marc'Aurelio Ranzato.
[
3
] Our paper on learning general purpose
    
distributed representations of sentences
 was accepted.
    at 
ICLR 2018.
 [Code][Paper]

*******
Contact
*******

sandeep.subramanian.1@umontreal.ca
GitHub Google Scholar Curriculum Vitae
--more--

************
Publications
************

 [
1
] 
 Multiple Attribute Text-Rewriting
 
      [ICLR 2019 (Under Review)]

 [
2
] 
 Towards Text Generation with Adversarilly 
  
 
     Learned Neural Outlines
 [NIPS 2018]

 [
3
] 
 Fortified Networks: Improving the 
 
     Robustness of Deep Networks by Modeling 
 
     the Manifold of Hidden Representations 
      [arXiv]

 [
4
] 
 Learning General Purpose Distributed 
 
     Sentence Representations via Large Scale 
 
 
     Multi-task Learning 
[ICLR 2018]

 [
5
] 
 Deep Complex Networks
 [ICLR 2018]

 [
6
] 
 A Deep Reinforcement Learning Chatbot
      [NIPS 2017 Demo] 

 [
7
] 
 Neural Models for Key Phrase Detection 
     
 and Question Generation 
      [ACL 2018 MRQA Workshop]
 
 [
8
] 
 Adversarial Generation of Natural Language
      [ACL 2017 REPL4NLP]

 [
9
] 
 Machine Comprehension by Text-to-Text
     
 Neural Question Generation
 
      [ACL 2017 REPL4NLP] 

 [
10
] 
Neural architectures for named entity  
     
 recognition 
[NAACL 2016]
 
 [
11
] 
A pilot study on the prevalence of DNA 
 
     
 palindromes in breast cancer genomes
 [BMC]

*********
Reviewing
*********

 [
1
] NIPS (2018) / ICML (2018) / NIPS (2017) 

 
Credits to Varsha Embar for the design idea and @boredyannlecun for the quote.