Compositional Text-to-Image Generation
Faithfully composing objects, attributes, and relations.
We design test-time strategies that improve compositional control in text-to-image generation. Our work addresses missing objects, attribute binding, and relational failures by enforcing stronger alignment between textual descriptions and visual elements.
Publications
-
TMLR 2026
CARINOX: Inference-Time Scaling with Category-Aware Reward-Based Initial Noise Optimization and Exploration
Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad, Niki Sepasian, Shayan Baghayi Nejad, MohammadAmin Fazli, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Improves compositional text-to-image generation by optimizing and exploring initial noise with category-aware rewards at inference time.
Transactions on Machine Learning Research (TMLR), 2026
-
ICASSP 2026
No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
Mohammad Hadi Sameti, Amir Mohammad Mansourian, Arash Marioriyad, Seyed Farid Oshyani, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Optimizes generation at test time to preserve every requested concept and improve compositional prompt fidelity.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026
-
TMLR 2025
Attention Overlap Is Responsible for the Entity Missing Problem in Text-to-Image Diffusion Models!
Arash Marioriyad, Mohammadali Banayeeanzade, Reza Abbasi, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Connects missing entities in generated images to overlapping attention maps and develops an inference-time strategy for better object coverage.
Transactions on Machine Learning Research (TMLR), 2025
-
TMLR 2025
Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-Image Models
Parham Rezaei, Arash Marioriyad, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Takes a probabilistic view of spatial relationships to improve how text-to-image models place and align objects described in prompts.
Transactions on Machine Learning Research (TMLR), 2025
-
arXiv 2025
Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models
Hamed Shahabadi, Niki Sepasian, Arash Marioriyad, Ali Sharifi-Zarchi, Mahdieh Soleymani Baghshah
Compares compositional alignment in visual autoregressive and diffusion models to expose their distinct strengths and failure modes.
arXiv preprint, 2025
-
arXiv 2025
Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad, Niki Sepasian, MohammadAmin Fazli, Mahdieh Soleymani Baghshah
Systematically evaluates whether popular metrics reliably measure object, attribute, and relationship alignment in generated images.
arXiv preprint, 2025
-
arXiv 2025
T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation
Seyed Mohammad Hadi Hosseini, Amirmohammad Izadi, Ali Abdollahi, Armin Saghafian, Mahdieh Soleymani Baghshah
Introduces a fine-grained metric for measuring whether generated images satisfy the individual components of complex prompts.
arXiv preprint, 2025
-
arXiv 2025
Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
Amirmohammad Izadi, Seyed Mohammad Hadi Hosseini, Soroush Vafaie Tabar, Ali Abdollahi, Armin Saghafian, Mahdieh Soleymani Baghshah
Refines alignment signals and initial noise to improve compositional correctness without retraining the text-to-image model.
arXiv preprint, 2025
-
arXiv 2025
Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
Arash Marioriyad, Parham Rezaei, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Benchmarks diffusion and autoregressive image generators and analyzes their relative ability to follow compositional prompts.
arXiv preprint, 2025