Related papers: IAR2: Improving Autoregressive Visual Generation w…

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…

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i.e. accurately generating entities with specified attributes and locations.…

Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-specific problems. Traditional RAG systems primarily rely on…

The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

In this work, we present VARGPT-v1.1, an advanced unified visual autoregressive model that builds upon our previous framework VARGPT. The model preserves the dual paradigm of next-token prediction for visual understanding and next-scale…

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

Text-to-image generation with visual autoregressive~(VAR) models has recently achieved impressive advances in generation fidelity and inference efficiency. While control mechanisms have been explored for diffusion models, enabling precise…

Owe to the powerful generative priors, the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However, as a consequence of the heavy quality…

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…

We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into…

Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present…

In this paper we tackle Image Super Resolution (ISR), using recent advances in Visual Auto-Regressive (VAR) modeling. VAR iteratively estimates the residual in latent space between gradually increasing image scales, a process referred to as…

As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typically rely on data replay or coarse binary supervision, which fails to explicitly…

We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face…

We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models…

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…