activity
20242026
collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2026

Localizing Knowledge in Diffusion Transformers

Arman Zarei, Samyadeep Basu, Keivan Rezaei +3

Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has e…

cs.CV2025

Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings

Arman Zarei, Keivan Rezaei, Samyadeep Basu +4

Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image genera…

cs.CV2024

On Mechanistic Knowledge Localization in Text-to-Image Generative Models

Samyadeep Basu, Keivan Rezaei, Priyatham Kattakinda +5

Identifying layers within text-to-image models which control visual attributes can facilitate efficient model editing through closed-form updates. Recent work, leveraging causal tr…

cs.CV2024

PRIME: Prioritizing Interpretability in Failure Mode Extraction

Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri +1

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by…

cs.CV2024

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei +4

In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materia…