相关论文: LINA: Linear Autoregressive Image Generative Model…

Autoregressive models have shown remarkable success in image generation by adapting sequential prediction techniques from language modeling. However, applying these approaches to images requires discretizing continuous pixel data through…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

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…

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few…

Recently, prompt learning has emerged as the state-of-the-art (SOTA) for fair text-to-image (T2I) generation. Specifically, this approach leverages readily available reference images to learn inclusive prompts for each target Sensitive…

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and…

Recent years, learned image compression has made tremendous progress to achieve impressive coding efficiency. Its coding gain mainly comes from non-linear neural network-based transform and learnable entropy modeling. However, most studies…

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…

Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory…

Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…

Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce this cost to…

Text-to-image (T2I) generative models, such as Stable Diffusion and DALL-E, have shown remarkable proficiency in producing high-quality, realistic, and natural images from textual descriptions. However, these models sometimes fail to…

Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or…

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger…

Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on…

Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent…

Linear recurrent neural networks have emerged as efficient alternatives to the original Transformer's softmax attention mechanism, thanks to their highly parallelizable training and constant memory and computation requirements at inference.…