Related papers: DPAR: Dynamic Patchification for Efficient Autoreg…

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training…

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…

Autoregressive conditional image generation models have emerged as a dominant paradigm in text-to-image synthesis. These methods typically convert images into one-dimensional token sequences and leverage the self-attention mechanism, which…

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to…

Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets,…

Visual Autoregressive Models (VAR) offer efficient and high-quality image generation but suffer from computational redundancy due to repeated Transformer calls at increasing resolutions. We introduce a dynamic Mixture-of-Experts router…

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding diversity. Inspired…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…

Recent progress in controllable image generation and editing is largely driven by diffusion-based methods. Although diffusion models perform exceptionally well in specific tasks with tailored designs, establishing a unified model is still…

Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generation and iterative denoising. In this work, we tackle this…

In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the…

Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into non-causal sequences or enforce heuristic orderings that…

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial…

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The…

Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the…

Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment,…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…