9 papers
ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani +4
Text-to-image diffusion models fail predictably on compositional prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent…
MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World Models
Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam +2
World Models are appearing as the next major frontier in computer vision. However, their robustness is currently largely unexplored. We identify the phenomenon of hallucination in…
Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
Soyoun Won, Aryan Yazdan Parast, Basim Azam +2
Text-to-image (T2I) diffusion models often fail to faithfully render explicit textual descriptions, instead defaulting to strongly learned visual priors due to a phenomenon referre…
Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam +2
Self-supervised video models are increasingly framed as world models, yet they are still evaluated almost entirely on clean video and reported as a final task score, obscuring how…
HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations
Aryan Yazdan Parast, Khawar Islam, Soyoun Won +2
Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not h…
Shortest-Path Flow Matching with Mixture-Conditioned Bases for OOD Generalization to Unseen Conditions
Andrea Rubbi, Amir Akbarnejad, Mohammad Vali Sanian +10
Robust generalization under distribution shift remains a key challenge for conditional generative modeling: conditional flow-based methods often fit the training conditions well bu…
GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
Aryan Yazdan Parast, Parsa Hosseini, Hesam Asadollahzadeh +4
Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the image. This weakness of MLLMs…
DDB: Diffusion Driven Balancing to Address Spurious Correlations
Aryan Yazdan Parast, Basim Azam, Naveed Akhtar
Deep neural networks trained with Empirical Risk Minimization (ERM) perform well when both training and test data come from the same domain, but they often fail to generalize to ou…
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
Fahimeh Hosseini Noohdani, Parsa Hosseini, Aryan Yazdan Parast +2
While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samp…