Related papers: Mechanistic Interpretability of Diffusion Models: …

This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are…

Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional perceptual similarity…

We introduce an approach for analyzing the variation of features generated by convolutional neural networks (CNNs) with respect to scene factors that occur in natural images. Such factors may include object style, 3D viewpoint, color, and…

Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-consuming processes.…

An experimental study on detecting synthetic face images is presented. We collected a dataset, called FF5, of five fake face image generators, including recent diffusion models. We find that a simple model trained on a specific image…

Recent advances in diffusion models have enabled the creation of deceptively real images, posing significant security risks when misused. In this study, we empirically show that different timesteps of DDIM inversion reveal varying subtle…

Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their stability. In this work, we argue that circuit discovery is…

A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create…

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape…

Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to…

Standard diffusion models are flexible estimators of complex distributions, but they do not encode causal structures and therefore do not by themselves support causal analysis. We propose a causality-encoded diffusion framework that…

We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of…

This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation step, we identify that not all operations are equally…

Super-resolution algorithms often struggle with images from surveillance environments due to adverse conditions such as unknown degradation, variations in pose, irregular illumination, and occlusions. However, acquiring multiple images,…

The perceptual representations supporting our ability to recognize faces remain a computational mystery. Deep neural networks offer mechanistic hypotheses for human face perception, but theoretically distinct models often make…

Deepfake detection research has largely converged on deep learning approaches that, despite strong benchmark performance, offer limited insight into what distinguishes real from manipulated facial behavior. This study presents an…

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results,…

Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent…

Diffusion models are capable of impressive feats of image generation with uncommon juxtapositions such as astronauts riding horses on the moon with properly placed shadows. These outputs indicate the ability to perform compositional…

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…