Parham RezaeiI'm a final year undergraduate student in Computer Engineering at Sharif University of Technology. I am interested in understanding deep generative models in order to better steer the distributions they produce. Most of my undergraduate research has centered around this direction. I am particularly drawn to studying generative models from a statistical perspective. Recently, I have become especially interested in sampling methods and the theory of flow models to build more controllable and efficient generative models. Email / GitHub / Google Scholar / LinkedIn |
|
Publications |
|
High-dimensional Analysis of Synthetic Data SelectionParham Rezaei, Filip Kovacevic, Francesco Locatello, Marco Mondelli PriGM Wrokshop @ EurIPS25 (Shorter Version), Under Review, 2025 arxiv / code / website / We analyzed augmenting data from a generative model from the perspective of random matrix theory. |
|
Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image ModelsParham Rezaei, Arash Mari Oriyad, M.S. Baghshah, M.H. Rohban TMLR, 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 ModelsParham 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 ModelsArash 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 ExperiencesI have been fortunate to work with some amazing researchers and professors. |
||||||||||
|
TeachingThese 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 ProjectsThese include coursework, side projects and unpublished research work. (To be updated) |
|
A 3D Tennis Complete AnalysisSharif 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. |
MiscellaneousI like reading (lately mostly Kafka), playing tennis (if tennis elbow allows :( ), and hiking. |
|
Design and source code from Jon Barron's website |