12 papers
Hidden Meanings in Plain Sight: RebusBench for Evaluating Cognitive Visual Reasoning
Seyed Amir Kasaei, Arash Marioriyad, Mahbod Khaleti +3
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a cr…
Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing
Arash Marioriyad, Ali Nouri, Mohammad Hossein Rohban +1
As Large Language Models (LLMs) transition into autonomous agentic roles, the risk of deception-defined behaviorally as the systematic provision of false information to satisfy ext…
Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models
Hossein Shahabadi, Niki Sepasian, Arash Marioriyad +2
Achieving compositional alignment between textual descriptions and generated images - covering objects, attributes, and spatial relationships - remains a core challenge for modern…
The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge
Arash Marioriyad, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Large language models (LLMs) are increasingly deployed as automatic judges to evaluate system outputs in tasks such as summarization, dialogue, and creative writing. A faithful jud…
Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning
Arash Marioriyad, Shaygan Adim, Nima Alighardashi +2
Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what exten…
No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
Mohammad Hossein Sameti, Amir M. Mansourian, Arash Marioriyad +3
Despite recent advances in text-to-image (T2I) models, they often fail to faithfully render all elements of complex prompts, frequently omitting or misrepresenting specific objects…
Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad +4
Text-image generation has advanced rapidly, but assessing whether outputs truly capture the objects, attributes, and relations described in prompts remains a central challenge. Eva…
CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad +5
Text-to-image diffusion models, such as Stable Diffusion, can produce high-quality and diverse images but often fail to achieve compositional alignment, particularly when prompts d…
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…
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…
Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!
Arash Marioriyad, Mohammadali Banayeeanzade, Reza Abbasi +2
Text-to-image diffusion models, such as Stable Diffusion and DALL-E, are capable of generating high-quality, diverse, and realistic images from textual prompts. However, they somet…
GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models
Ali Abdollahi, Mahdi Ghaznavi, Mohammad Reza Karimi Nejad +6
Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well i…