I am currently a 3rd year PhD candidate at EPFL Lausanne pursuing my doctoral studies under
supervision of Sabine Süsstrunk at Image and
Visual Representation Laboratory (IVRL) .
Before joining EPFL, I did my bachelor's degree in Computer Engineering at
Sharif University of Technology in Iran.
During the summer of 2018, I had the opportunity to undertake an internship at IST Austria
where I was mentored by Christoph Lampert. In the following year, from 2019 to 2020, I
worked as a Data Scientist at Balad, a dynamic company
dedicated to the development of advanced map and navigation software.
During my high school years, I developed a strong passion for Physics and dedicated
considerable effort to preparing for the national physics Olympiad, where I was able to
achieve the 7th rank among a vast pool of nearly 100 thousand participants and earn a gold
medal.
Throughout my bachelor's degree, I found myself deeply intrigued by the world of probability
and statistics. My interest led me to take part in the national statistics Olympiad, where I
achieved the 1st place among hundreds of participants and awarded a gold medal.
I'm interested in Computer Vision and Computer Graphics, and Machine Learning. I like to
design simple
(physics and bio)-inspired models to efficiently solve different tasks in Computer Vision
and Computer
Graphics. At the moment, my research is focused on
Neural cellular automata models and self-organizing systems
We introduce the Locally Effective Latent Space Direction (LELSD) framework, a novel
approach to localized image editing in Generative Adversarial Networks (GANs), which
utilizes a new objective function incorporating supervision from a pre-trained segmentation
network.
We present an uncomplicated non-parametric baseline that attains the lowest error based on a
widely adopted metric within the field. This serves to demonstrate the misleading nature of
this particular metric.