Related papers: On Inductive Biases That Enable Generalization of …

Diffusion Transformers (DiTs) have recently gained substantial attention in both industrial and academic fields for their superior visual generation capabilities, outperforming traditional diffusion models that use U-Net. However,the…

Domain generalisation involves pooling knowledge from source domain(s) into a single model that can generalise to unseen target domain(s). Recent research in domain generalisation has faced challenges when using deep learning models as they…

Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large transformer models, which result in substantial training…

The capability of generalization is a cornerstone for the success of modern learning systems. For non-Euclidean data, e.g., graphs, that particularly involves topological structures, one important aspect neglected by prior studies is how…

Diffusion models have shown remarkable performance in image generation in recent years. However, due to a quadratic increase in memory during generating ultra-high-resolution images (e.g. 4096*4096), the resolution of generated images is…

Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic…

Diffusion Transformers (DiTs) have recently attracted significant interest from both industry and academia due to their enhanced capabilities in visual generation, surpassing the performance of traditional diffusion models that employ…

Diffusion models have recently gained state of the art performance on many image generation tasks. However, most models require significant computational resources to achieve this. This becomes apparent in the application of medical image…

Diffusion models struggle to produce samples that respect constraints, a common requirement in scientific applications. Recent approaches have introduced regularization terms in the loss or guidance methods during sampling to enforce such…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

The audio denoising technique has captured widespread attention in the deep neural network field. Recently, the audio denoising problem has been converted into an image generation task, and deep learning-based approaches have been applied…

Transformers, with their self-attention mechanisms for modeling long-range dependencies, have become a dominant paradigm in image restoration tasks. However, the high computational cost of self-attention limits scalability to…

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

This paper develops doubly robust estimators for direct (DATT) and spillover (SATT) average treatment effects on the treated in network-based difference-in-differences (DiD) designs. Unlike standard DiD methods, the proposed approach…

Graph Transformers (GTs) have shown strong empirical performance, yet current architectures vary widely in their use of attention mechanisms, positional embeddings (PEs), and expressivity. Existing expressivity results are often tied to…

Transformers are often the go-to architecture to build foundation models that ingest a large amount of training data. But these models do not estimate the probability density distribution when trained on regression problems, yet obtaining…

Machine learning models struggle with generalization when encountering out-of-distribution (OOD) samples with unexpected distribution shifts. For vision tasks, recent studies have shown that test-time adaptation employing diffusion models…

Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process…

When models, e.g., for semantic segmentation, are applied to images that are vastly different from training data, the performance will drop significantly. Domain adaptation methods try to overcome this issue, but need samples from the…

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…