Related papers: MADFormer: Mixed Autoregressive and Diffusion Tran…

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image…

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for…

Diffusion models have recently gained prominence as powerful deep generative models, demonstrating unmatched performance across various domains. However, their potential in multi-sensor fusion remains largely unexplored. In this work, we…

Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models…

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the…

Transparent image layer generation plays a significant role in digital art and design workflows. Existing methods typically decompose transparent layers from a single RGB image using a set of tools or generate multiple transparent layers…

In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of…

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image context in a linear 1D order by…

Autoregressive models are predominant in natural language generation, while their application in tabular data remains underexplored. We posit that this can be attributed to two factors: 1) tabular data contains heterogeneous data type,…

Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual synthesis remains challenging. We present MammothModa2…

Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transformers), while largely overlooking the potential of…

Diffusion-based image generators can now produce high-quality and diverse samples, but their success has yet to fully translate to 3D generation: existing diffusion methods can either generate low-resolution but 3D consistent outputs, or…

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…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…