2 papers
cs.CV2025
Deeper Diffusion Models Amplify Bias
Shahin Hakemi, Naveed Akhtar, Ghulam Mubashar Hassan +1
Despite the remarkable performance of generative Diffusion Models (DMs), their internal working is still not well understood, which is potentially problematic. This paper focuses o…
cs.CV2025
Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization
Shahin Hakemi, Naveed Akhtar, Ghulam Mubashar Hassan +1
Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with…