Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model

MAVias is an innovative approach aimed at mitigating biases in computer vision models, which is crucial for enhancing the trustworthiness of artificial intelligence systems. Traditional bias mitigation techniques often address a limited range of predefined biases, which restricts their effectiveness in diverse visual datasets that may contain multiple, unknown biases. MAVias utilizes foundation models to identify spurious associations between visual attributes and target classes, capturing a broad spectrum of visual features and translating them into language-coded potential biases for further…

The study benchmarks various deep learning-based object detection models using the MobilTelesco dataset, which features sparse astrophotography images. Traditional datasets like ImageNet and COCO focus on everyday objects, lacking the unique challenges presented by feature-deficient conditions. The research highlights the difficulties these models face when applied to non-commercial domains, emphasizing the need for specialized datasets in astrophotography.

The article discusses a novel approach to enhancing the diversity of outputs in Fractal Generative Models (FGMs) while maintaining high visual quality. By incorporating the Hausdorff Dimension (HD), a concept from fractal geometry that quantifies structural complexity, the authors propose a learnable HD estimation method that predicts HD from image embeddings. This method aims to improve the diversity of generated images, addressing challenges such as image quality degradation and limited diversity enhancement in FGMs.

The article discusses a novel approach called ODE$_t$(ODE$_l$) that optimizes the sampling process in continuous normalizing flows (CNFs) and diffusion models (DMs). By rewiring transformer-based architectures and introducing a length consistency term, this method reduces computational complexity and allows for flexible sampling with varying time steps and transformer blocks. This advancement aims to enhance the efficiency and quality of data generation from noise distributions.

The article discusses the vulnerabilities of certified defenses in machine learning, particularly in the context of adversarial attacks. It highlights how malicious actors can exploit probabilistic certification frameworks to mislead classifiers and generate false robustness guarantees for adversarial inputs. The study reveals that small, imperceptible perturbations can be crafted to spoof certification processes, raising concerns about the reliability of certified models in real-world applications.

MeanFlow (MF) is a generative model inspired by diffusion processes, designed for efficient few-step generation by learning direct transitions from noise to data. It is commonly utilized as a latent MF, employing the pre-trained Stable Diffusion variational autoencoder (SD-VAE) for high-dimensional data modeling. However, MF training is computationally intensive and often unstable. This study introduces an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE), addressing issues like gradient explosion during training.