51 citations · 64 across the 17 of their papers we have counts for
17 papers
MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara +1
Multimodal Large Language Models (MLLMs) have experienced rapid progress in visual recognition tasks in recent years. Given their potential integration into many critical applicati…
A Critical Review of Predominant Bias in Neural Networks
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3
Bias issues of neural networks garner significant attention along with its promising advancement. Among various bias issues, mitigating two predominant biases is crucial in advanci…
Look, Learn and Leverage (L): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment
Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei +2
Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal str…
An Investigation on The Position Encoding in Vision-Based Dynamics Prediction
Jiageng Zhu, Hanchen Xie, Jiazhi Li +2
Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environm…
ManiFPT: Defining and Analyzing Fingerprints of Generative Models
Hae Jin Song, Mahyar Khayatkhoei, Wael AbdAlmageed
Recent works have shown that generative models leave traces of their underlying generative process on the generated samples, broadly referred to as fingerprints of a generative mod…
Exploring Perceptual Limitation of Multimodal Large Language Models
Jiarui Zhang, Jinyi Hu, Mahyar Khayatkhoei +2
Multimodal Large Language Models (MLLMs) have recently shown remarkable perceptual capability in answering visual questions, however, little is known about the limits of their perc…
SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising meth…
Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks
Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising met…
Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies
Mulin Tian, Mahyar Khayatkhoei, Joe Mathai +1
Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepf…
Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara +1
Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream a…
Shadow Datasets, New challenging datasets for Causal Representation Learning
Jiageng Zhu, Hanchen Xie, Jianhua Wu +4
Discovering causal relations among semantic factors is an emergent topic in representation learning. Most causal representation learning (CRL) methods are fully supervised, which i…
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions
Mahyar Khayatkhoei, Wael AbdAlmageed
Precision and Recall are two prominent metrics of generative performance, which were proposed to separately measure the fidelity and diversity of generative models. Given their cen…
A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei +3
Dynamics prediction, which is the problem of predicting future states of scene objects based on current and prior states, is drawing increasing attention as an instance of learning…
Using Visual Cropping to Enhance Fine-Detail Question Answering of BLIP-Family Models
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara +1
Visual Question Answering is a challenging task, as it requires seamless interaction between perceptual, linguistic, and background knowledge systems. While the recent progress of…
Spatial Frequency Bias in Convolutional Generative Adversarial Networks
Mahyar Khayatkhoei, Ahmed Elgammal
As the success of Generative Adversarial Networks (GANs) on natural images quickly propels them into various real-life applications across different domains, it becomes more and mo…
Disconnected Manifold Learning for Generative Adversarial Networks
Mahyar Khayatkhoei, Ahmed Elgammal, Maneesh Singh
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative A…
Interactive Diversity Optimization of Environments
Glen Berseth, Mahyar Khayatkhoei, Brandon Haworth +3
The design of a building requires an architect to balance a wide range of constraints: aesthetic, geometric, usability, lighting, safety, etc. At the same time, there are often a m…