The softmax operator is a crucial component of large language models (LLMs), which have
played a transformative role in computer research. Due to the centrality of the softmax …

Inspired by recent advances in diffusion models, which are reminiscent of denoising
autoencoders, we investigate whether they can acquire discriminative representations for …

Diffusion models are generative models, which gradually add and remove noise to learn the
underlying distribution of training data for data generation. The components of diffusion …

We present a single neural network architecture composed of task-agnostic components
(ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav (" …

In this paper, we address the performance degradation of efficient diffusion models by
introducing Multi-architecturE Multi-Expert diffusion models (MEME). We identify the need for …

Diffusion models have emerged as the de-facto technique for image generation, yet they
entail significant computational overhead, hindering the technique's broader application in …

Transformer-based diffusion models have achieved significant advancements across a
variety of generative tasks. However, producing high-quality outputs typically necessitates …

In recent years, the field of deep learning has experienced a surge in the popularity of
generative models, largely propelled by the transformative influence of Generative …

Recent advances have demonstrated the powerful capability of transformer architecture in
image restoration. However, our analysis indicates that existing transformerbased methods …

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for
latent-space image generation. With an isotropic architecture that chains a series of …