Parham Rezaei

I am an undergraduate in Computer Engineering at Sharif University of Technology.

Last summer, I had the previlege to work under the supervision of Prof. Farnia at CUHK. We explored Multi-Armed bandit approaches to online learning of the optimal mixture of models.

Before that, I collaborated with Prof. M. Soleymani and Prof. M.H. Rohban at Sharif, working on compositional generation and methods to enhance spatial relationship alignment in text-to-image diffusion models.

Two summers ago, I interned at the L3S Research Center, where we explored ways to improve the CLIP score for uncovering the reasoning behind image classification.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

Research

I am in love with generative models. Especially, in 3D.

Be More Diverse than the Most Diverse: Online Selection of Diverse Mixtures of Generative Models

We proposed an online algorithm for finding the optimal mixture of generative models.

Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models

We investigated the performance of diffusion models in text-to-image generation tasks. We found that diffusion models outperform autoregressive models in terms of compositional generation.

Other Projects

These include coursework, side projects and unpublished research work.

A 3D Tennis Complete Analysis

Used both classical computer vision techniques and deep learning models to automate the process of analyzing tennis matches.

Design and source code from Jon Barron's website