Youssef Mroueh

Title

Principal Research Scientist

Bio

Youssef Mroueh is a Principal Research Scientist in IBM since April 2015. He received his PhD in computer science in February 2015 from MIT, CSAIL, where he was advised by Professor Tomaso Poggio.

In 2011, he obtained his engineering diploma from Ecole Polytechnique Paris France, and a master of science in Applied Maths from Ecole des Mines de Paris.

He is interested in Deep Learning, Machine Learning, Optimal transport, multimodal learning, Statistical Learning Theory, Computer Vision and Artificial Intelligence.

Publications

Adversarial semantic alignment for improved image captions
- - Pierre Dognin
  - Igor Melnyk
  - et al.
- 2019
- CVPR 2019
Improved adversarial image captioning
- - Pierre Dognin
  - Igor Melnyk
  - et al.
- 2019
- DGS@ICLR Workshop 2019
Wasserstein barycenter model ensembling
- - Pierre Dognin
  - Igor Melnyk
  - et al.
- 2019
- ICLR 2019
Sobolev descent
- - Youssef Mroueh
  - Tom Sercu
  - et al.
- 2019
- AISTATS 2019
Implicit kernel learning
- - Chun Liang Li
  - Wei Cheng Chang
  - et al.
- 2019
- AISTATS 2019
Sobolev Gan
- - Youssef Mroueh
  - Chun Liang Li
  - et al.
- 2018
- ICLR 2018
Fisher GAN
- - Youssef Mroueh
  - Tom Sercu
- 2017
- NeurIPS 2017
Self-critical sequence training for image captioning
- - Steven Rennie
  - Etienne Marcheret
  - et al.
- 2017
- CVPR 2017
McGan: Mean and covariance feature matching GAN
- - Youssef Mroueh
  - Tom Sercu
  - et al.
- 2017
- ICML 2017
Local group invariant representations via orbit embeddings
- - Anant Raj
  - Abhishek Kumar
  - et al.
- 2017
- AISTATS 2017

Visit Google Scholar

Patents

- 04 Dec 2023
- US
- 11836220
Updating Of Statistical Sets For Decentralized Distributed Training Of A Machine Learning Model
- 08 May 2023
- US
- 11645555
Feature Selection Using Sobolev Independence Criterion
- 24 Apr 2023
- US
- 11636280
Updating Of Statistical Sets For Decentralized Distributed Training Of A Machine Learning Model
- 17 Apr 2023
- US
- 11630989
Mutual Information Neural Estimation With Eta-trick
- 27 Jun 2022
- US
- 11373760
False Detection Rate Control With Null-hypothesis
- 07 Dec 2020
- US
- 10860900
Transforming Source Distribution To Target Distribution Using Sobolev Descent

Blog posts

An AI foundation model that learns the grammar of molecules
News
Payel Das, Youssef Mroueh, Inkit Padhi, Vijil Chenthamarakshan, Jerret Ross, and Brian Belgodere
25 Jan 2023
AI boosts the discovery of metamaterials vital for next-gen gadgets
Research
Youssef Mroueh, Karthikeyan Shanmugam, and Payel Das
20 May 2021
10 minute read
Image captioning as an assistive technology
News
Youssef Mroueh
23 Jul 2020
5 minute read

Top collaborators

Youssef Mroueh

Title

Bio

Publications

Adversarial semantic alignment for improved image captions

Improved adversarial image captioning

Wasserstein barycenter model ensembling

Sobolev descent

Implicit kernel learning

Sobolev Gan

Fisher GAN

Self-critical sequence training for image captioning

McGan: Mean and covariance feature matching GAN

Local group invariant representations via orbit embeddings

Patents

Updating Of Statistical Sets For Decentralized Distributed Training Of A Machine Learning Model

Feature Selection Using Sobolev Independence Criterion

Updating Of Statistical Sets For Decentralized Distributed Training Of A Machine Learning Model

Mutual Information Neural Estimation With Eta-trick

False Detection Rate Control With Null-hypothesis

Transforming Source Distribution To Target Distribution Using Sobolev Descent

Blog posts

An AI foundation model that learns the grammar of molecules

AI boosts the discovery of metamaterials vital for next-gen gadgets

Image captioning as an assistive technology

Top collaborators

Kristjan Greenewald

Mattia Rigotti

Mikhail Yurochkin

Yuhai Tu