ISI Directory

Mahyar Khayatkhoei, Ph.D.

Publications

2025
MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski
arXiv preprint arXiv:2502.17422,  2025
View Paper
A Critical Review of Predominant Bias in Neural Networks
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed
arXiv preprint arXiv:2502.11031,  2025
View Paper
2024
Look, Learn and Leverage (L): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment
Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei, Jiazhi Li, Wael AbdAlmageed
arXiv preprint arXiv:2408.17363,  2024
View Paper
An investigation on the position encoding in vision-based dynamics prediction
Jiageng Zhu, Hanchen Xie, Jiazhi Li, Mahyar Khayatkhoei, Wael AbdAlmageed
arXiv preprint arXiv:2408.15201,  2024
View Paper
Exploring perceptual limitation of multimodal large language models
Jiarui Zhang, Jinyi Hu, Mahyar Khayatkhoei, Filip Ilievski, Maosong Sun
arXiv preprint arXiv:2402.07384,  2024
View Paper
Multi-Scope Representation Learning for Causal Relations Discovery with New Challenging Datasets
Jiageng Zhu, Hanchen Xie, Jianhua Wu, Mohamed E Hussein, Mahyar Khayatkhoei, Jiazhi Li, Wael AbdAlmageed
Mouth 3, 4,  2024
View Paper
Manifpt: Defining and analyzing fingerprints of generative models
Hae Jin Song, Mahyar Khayatkhoei, Wael AbdAlmageed
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …,  2024
View Paper
2023
Unsupervised multimodal deepfake detection using intra-and cross-modal inconsistencies
Mulin Tian, Mahyar Khayatkhoei, Joe Mathai, Wael AbdAlmageed
arXiv preprint arXiv:2311.17088,  2023
View Paper
SABAF: Removing strong attribute bias from neural networks with adversarial filtering
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed
arXiv preprint arXiv:2311.07141,  2023
View Paper
Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed
arXiv preprint arXiv:2310.04955,  2023
View Paper
Shadow datasets, new challenging datasets for causal representation learning
Jiageng Zhu, Hanchen Xie, Jianhua Wu, Jiazhi Li, Mahyar Khayatkhoei, Mohamed E Hussein, Wael AbdAlmageed
arXiv preprint arXiv:2308.05707,  2023
View Paper
A critical view of vision-based long-term dynamics prediction under environment misalignment
Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei, Jiazhi Li, Mohamed E Hussein, Wael AbdAlmageed
International Conference on Machine Learning, 38258-38271,  2023
View Paper
Using visual cropping to enhance fine-detail question answering of blip-family models
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski
arXiv preprint arXiv:2306.00228,  2023
View Paper
Visual cropping improves zero-shot question answering of multimodal large language models
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski
R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation …,  2023
View Paper
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions
Mahyar Khayatkhoei, Wael AbdAlmageed
International Conference on Machine Learning, 16326-16343,  2023
View Paper
Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, Filip Ilievski
arXiv preprint arXiv:2310.16033,  2023
View Paper
2022
Spatial frequency bias in convolutional generative adversarial networks
Mahyar Khayatkhoei, Ahmed Elgammal
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7152-7159,  2022
View Paper
2021
Geometric and Spectral Limitations in Generative Adversarial Networks
Mahyar Khayatkhoei
Rutgers The State University of New Jersey, School of Graduate Studies,  2021
View Paper
2019
Interactive architectural design with diverse solution exploration
Glen Berseth, Brandon Haworth, Muhammad Usman, Davide Schaumann, Mahyar Khayatkhoei, Mubbasir Kapadia, Petros Faloutsos
IEEE transactions on visualization and computer graphics 27 (1), 111-124,  2019
View Paper
2018
Interactive Diversity Optimization of Environments
Glen Berseth, Mahyar Khayatkhoei, Brandon Haworth, Muhammad Usman, Mubbasir Kapadia, Petros Faloutsos
arXiv preprint arXiv:1801.08607,  2018
View Paper
Disconnected manifold learning for generative adversarial networks
Mahyar Khayatkhoei, Ahmed Elgammal, Maneesh Singh
Advances in Neural Information Processing Systems 31, 7354--7364,  2018
View Paper
2017
CODE: Crowd‐optimized design of environments
Brandon Haworth, Muhammad Usman, Glen Berseth, Mahyar Khayatkhoei, Mubbasir Kapadia, Petros Faloutsos
Computer Animation and Virtual Worlds 28 (6), e1749,  2017
View Paper
2016
Towards computer assisted crowd aware architectural design
Brandon Haworth, Muhammad Usman, Glen Berseth, Mahyar Khayatkhoei, Mubbasir Kapadia, Petros Faloutsos
Proceedings of the 2016 chi conference extended abstracts on human factors …,  2016
Using synthetic crowds to inform building pillar placements
Brandon Haworth, Muhammad Usman, Glen Berseth, Mahyar Khayatkhoei, Mubbasir Kapadia, Petros Faloutsos
2016 IEEE Virtual Humans and Crowds for Immersive Environments (VHCIE), 7-11,  2016
View Paper
2015
A low-cost vision-based system for displacement analysis in earthquake research
Bijan Binaee, Mahyar Khayatkhoei, Hadi Moradi, Amirhossein Nazemi, Abdollah Hosseini
2015 3rd RSI International Conference on Robotics and Mechatronics (ICROM …,  2015