Yassine Yousfi
I am passionate about machine intelligence.
I work as a head of Machine Learning at comma.ai where my focus is learning driving agents from data and in an end-to-end fashion.
To do so, we’re training World Models for driving. These World Models can be seen as “simulators” generating realistic driving video given driving inputs (steering, gas, etc.). World Models are useful for many reasons:
- They are trained with very little supervision (self-supervised training)
- They can be used to generate synthetic data for other models to learn on-policy
- They can be used as powerful feature extractors
- They can be used as policies
I hold a PhD in Electrical and Computer Engineering from Binghamton University (SUNY) where I researched digital media security topics such as Steganography/Steganalysis or Watermarking Deep Learning.
The take-away from my PhD was that when carefully scaling Machine Learning architecture and data, digital media security tasks can be learned end-to-end, with little domain specific preprocessing or tricks.
I also hold a MSc in Computer Science/Machine Learning from École Centrale de Lille (France).
News
Jun 25, 2023 | I’m giving a talk at comma_con titled “Learning a Driving Simulator.” Blog post coming soon. |
---|---|
Jun 1, 2023 | I’m serving as a Technical Program Chair for the 11th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) |
Jun 28, 2022 | Our new paper “Detector-Informed Batch Steganography and Pooled Steganalysis” won the Best Student Paper Award at the ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC)! |
May 10, 2022 | I successfully defended my Ph.D. dissertation 🎉 |
May 1, 2022 | Excited about our new paper on Batch Steganography and Pooled Steganalysis accepted at the ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC). |