Related papers: Mechanistic Interpretability of Diffusion Models: …

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases…

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

Facial Beauty Prediction (FBP) is a challenging computer vision task due to its subjective nature and the subtle, holistic features that influence human perception. Prevailing methods, often based on deep convolutional networks or standard…

Diffusion models have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of denoising noisy images that are difficult for experts to…

Large-scale facial datasets like CelebA are widely used in computer vision, yet the cultural biases embedded in their labels remain underexplored. Fairness research has distinguished representational from allocational harms, but audits of…

Generative foundation models like Stable Diffusion comprise a diverse spectrum of knowledge in computer vision with the potential for transfer learning, e.g., via generating data to train student models for downstream tasks. This could…

Recent advancements in vision models have greatly improved their ability to handle complex chart understanding tasks, like chart captioning and question answering. However, it remains challenging to assess how these models process charts.…

Face parsing is a fundamental task in computer vision, enabling applications such as identity verification, facial editing, and controllable image synthesis. However, existing face parsing models often lack fairness and robustness, leading…

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia…

Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the…

This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance imaging (MRI) synthesis. Although diffusion models have shown strong performance in generating…

Deep generative models have shown impressive results in generating realistic images of faces. GANs managed to generate high-quality, high-fidelity images when conditioned on semantic masks, but they still lack the ability to diversify their…

Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets.…

Recent advancements in generative AI, particularly diffusion-based image editing, have enabled the transformation of images into highly realistic scenes using only text instructions. This technology offers significant potential for…

Diffusion models have emerged from various theoretical and methodological perspectives, each offering unique insights into their underlying principles. In this work, we provide an overview of the most prominent approaches, drawing attention…

Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled new approaches to data…

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have…

The rapid evolution of digital image manipulation techniques poses significant challenges for content verification, with models such as stable diffusion and mid-journey producing highly realistic, yet synthetic, images that can deceive…

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…