Gabriel Huang (he/him)
PhD, Mila & University of Montreal
Visiting Researcher, ServiceNow
Update March 2022: I am looking for a full-time position to pursue research on Responsible AI.
Topics of interest: impact of AI on human behavior and social dynamics,
ethical and emotional AI,
aligning AI with humanist values,
self-supervised and low-data learning,
multimodal transformers,
and large language models.
Aligning AI with technical goals was a central theme of my PhD thesis, during which I have developed technical skills on multimodal language models, self-supervised and few-shot learning, object detection, optimal transport and generative learning. Now, I want to apply these technical skills to develop responsible and ethical AI aligned with humanist values, not only to ensure that individuals are treated fairly, but also to strengthen the core values of our societies (e.g. human life, truth, democracy, sustainability). I have recently started Naive Psychology, a blog to share my ideas on the interplay between AI, human behavior and society.
About me: I am a PhD student at Mila Quebec AI Institute advised by Simon Lacoste-Julien. Currently, I am a visiting researcher at ServiceNow (ElementAI) working on few-shot and self-supervised object detection, low-data language models, and self-supervised representations for climate change monitoring. Previously, I was an intern at Google Research working on multimodal pretraining for video captioning. I also hold two MSc. from Ecole Normale Supérieure and CentraleSupélec, where I specialized in machine learning, computer vision and statistics.
Below is an interactive visualization of our paper Negative Momentum for
Improved Game Dynamics:
(a) Learning rate (lr) and momentum (beta) hyperparameters.
(b) Resulting eigenvalues in the complex plane for SGD and SGD+momentum.
There is convergence if and only if all eigenvalues are inside the convergence ball (green).
Try to find the
hyperparameters for convergence.
SGD without momentum: using ,
eigenvalues are the convergence ball →
SGD with momentum: using
and momentum ,
eigenvalues are the convergence ball →
The Thin-8 dataset consists of 1585 grayscale handwritten images of the digit 8, with resolution
512x512.
16 people were asked to draw the digit 8 about 100 times using a pen on a tablet PC running Microsoft Windows.
It was collected in October 2017 at the University of Montreal.
Download Thin-8 dataset here
If you use the Thin-8 dataset, please cite our paper :
@article{huang2018parametric,
title={Parametric Adversarial Divergences are Good Task Losses for Generative Modeling},
author={Huang, Gabriel and Berard, Hugo and Touati, Ahmed and Gidel, Gauthier and Vincent, Pascal and Lacoste-Julien, Simon},
journal={arXiv preprint arXiv:1708.02511},
year={2017}
}
Thanks to Alex, Akram, Aristide, David, Dendi, Eugene, Jae, Joao, Liam, Rémi, Rosemary, Shawn, Sina, and Xing for scribbling all those samples!
Email: gbxhuang@gmail.com
In person: Mila, 6666 St-Urbain, #200, Montreal, QC, H2S 3H1, Canada