Related papers: Latent Causal Diffusions for Single-Cell Perturbat…

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed compared to purely discrete formulations. This gap is counterintuitive, given…

Change detection (CD) is fundamental to computer vision and remote sensing, supporting applications in environmental monitoring, disaster response, and urban development. Most CD models assume co-registered inputs, yet real-world imagery…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Current supervised learning can learn spurious correlation during the data-fitting process, imposing issues regarding interpretability, out-of-distribution (OOD) generalization, and robustness. To avoid spurious correlation, we propose a…

Diffusion-based generative models have demonstrated a capacity for perceptually impressive synthesis, but can they also be great likelihood-based models? We answer this in the affirmative, and introduce a family of diffusion-based…

Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks such as depth…

Conditional diffusion probabilistic models can model the distribution of natural images and can generate diverse and realistic samples based on given conditions. However, oftentimes their results can be unrealistic with observable color…

Causal representation learning (CRL) aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A…

Causal Disentangled Representation Learning(CDRL) aims to learn and disentangle low dimensional representations and their underlying causal structure from observations. However, existing disentanglement methods rely on a standard mean-field…

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…

Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion transitions. However, recent methods still exhibit noticeable limitations in preserving…

Diffusion models (DMs) have achieved remarkable success in image and video generation. However, they still struggle with (1) physical alignment and (2) out-of-distribution (OOD) instruction following. We argue that these issues stem from…

It has been suggested that generative image models such as diffusion models can improve performance on clinically relevant tasks by offering deep learning models supplementary training data. However, most conditional diffusion models treat…

This paper introduces StructDiff, a generative framework based on a single-scale diffusion model for single-image generation. Single-image generation aims to synthesize diverse samples with similar visual content to the source image by…

Robust machine learning for regulatory genomics is studied under biologically and technically induced distribution shifts. Deep convolutional and attention based models achieve strong in distribution performance on DNA regulatory sequence…

Lidar point cloud synthesis based on generative models offers a promising solution to augment deep learning pipelines, particularly when real-world data is scarce or lacks diversity. By enabling flexible object manipulation, this synthesis…

Diffusion Probabilistic Models (DPMs) suffer from inefficient inference due to their slow sampling and high memory consumption, which limits their applicability to various medical imaging applications. In this work, we propose a novel…

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma…

Existing single image reflection removal (SIRR) methods using deep learning tend to miss key low-frequency (LF) and high-frequency (HF) differences in images, affecting their effectiveness in removing reflections. To address this problem,…