collaborators

5 papers

cs.CV2026

(1D) Ordered Tokens Enable Efficient Test-Time Search

Zhitong Gao, Parham Rezaei, Ali Cy +7

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information,…

stat.ML2025

High-dimensional Analysis of Synthetic Data Selection

Parham Rezaei, Filip Kovacevic, Francesco Locatello +1

Despite the progress in the development of generative models, their usefulness in creating synthetic data that improve prediction performance of classifiers has been put into quest…

cs.CV2025

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

Parham Rezaei, Arash Marioriyad, Mahdieh Soleymani Baghshah +1

Despite the ability of text-to-image models to generate high-quality, realistic, and diverse images, they face challenges in compositional generation, often struggling to accuratel…

cs.LG2025

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms

Parham Rezaei, Farzan Farnia, Cheuk Ting Li

The availability of multiple training algorithms and architectures for generative models requires a selection mechanism to form a single model over a group of well-trained generati…

cs.CV2025

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

Arash Marioriyad, Parham Rezaei, Mahdieh Soleymani Baghshah +1

Text-to-image (T2I) generative models, such as Stable Diffusion and DALL-E, have shown remarkable proficiency in producing high-quality, realistic, and natural images from textual…