Parham Rezaei

I'm a final year undergraduate student in Computer Engineering at Sharif University of Technology.

Broadly speaking, I’m interested in generative models from both theoretical and practical perspectives. Most of my research has also been in this area. Currently, I’m focusing on inference-time scaling for autoregressive image generative models. By the way, I’m always open to opportunities to pursue theoretical research on flow models as well.

Email / GitHub / Google Scholar / LinkedIn

Publications

The following is what I have contributed to this field. I've found the projects fun, I hope you find them interesting too!

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models

Parham Rezaei, Arash Mari Oriyad, M.S. Baghshah, M.H. Rohban
Under Review, 2025
arxiv / code /

We proposed a new way to look at the spatial relationship alignment in T2I models and how to use it to improve the adherence of generated images to textual descriptions.

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

Parham Rezaei, Farzan Farnia, Cheuk Ting Li
ICLR, 2025
arxiv / code / website /

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

Arash Mari Oriyad, Parham Rezaei, M.S. Baghshah, M.H. Rohban
NeurIPS 2024 Workshop on Compositional Learning, 2024
arxiv /

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.

Research Experiences

I have been fortunate to work with some amazing researchers and professors.

EPFL RL on auto-regressive image generative models • Jun. 2025 to Now Advisor: Prof. Amir Zamir (VILAB)
ISTA Theoretical foundations of generative data augmentation • Feb. 2025 to Jun. 2025 Advisor: Prof. Marco Mondelli and Prof. Francesco Locatello
CUHK Optimizing mixture of generative models using mixture-ucb algorithms • Jul. 2024 to Oct. 2024 Advisor: Prof. Farzan Farnia
Sharif ML Lab Compositional generation and spatial accuracy in T2I models • Dec. 2023 to Jul. 2024 Advisor: Prof. Mahdieh Soleymani, Prof. Mohammad Hossein Rohban
L3S Research Center Improving rationales behind CLIP • Jul. 2023 to Oct. 2023 Advisor: Prof. Wolfgang Nejdl

Teaching

These include both teaching and non-paid TAing experiences.

TA

Deep Learning [Graduate]: Spring 2025, Sharif, with instructor: Mahdieh Soleymani

System 2 [Graduate]: Spring 2025, Sharif, with instructor: Mahdieh Soleymani

Advanced Programming: Spring 2024, Spring 2023, Sharif, with instructor: Mohammad Amin Fazli

Artificial Intelligence: Spring 2024, Fall 2023, Sharif, with instructor: Mohammad Hossein Rohban

Computer Simulation: Fall 2024 (Head), Spring 2024, Fall 2023, Sharif, with instructor: Bardia Safaei

Design of Algorithms: Spring 2024, Sharif, with instructor: Mohammad Ali Abam

Database Design: Spring 2024, Sharif, with instructor: Maryam Ramezani

Discrete Structures: Spring 2024, Sharif, with instructor: Hamid Zarrabi-Zadeh

Fundamentals of Programming: Fall 2023, Fall 2022, Sharif, with instructor: Mohammad Amin Fazli

Linear Algebra: Spring 2023, Fall 2023, Sharif, with instructor: Maryam Ramezani

Mathematics Olympiad Instructor

Allameh Tabatabei High School: Sep. 2022 to Jul. 2023, Teaching Algebra

Allameh Helli High School: Sep. 2021 to Jul. 2022, Teaching Combinatorics and Geometry

Other Projects

These include coursework, side projects and unpublished research work. (To be updated)

A 3D Tennis Complete Analysis

Sharif 3D Computer Vision
2023-10-05
paper / code /

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

Miscellaneous

I enjoy reading and playing tennis in my free time. I also love traveling and generally new adventures.

Design and source code from Jon Barron's website