Related papers: LINA: Linear Autoregressive Image Generative Model…

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…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) methods. However, NAT models often suffer from the…

Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited…

Recent advances in diffusion-based controllable visual generation have led to remarkable improvements in image quality. However, these powerful models are typically deployed on cloud servers due to their large computational demands, raising…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content control, and maintaining deep semantic consistency. Existing T2I…

Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined…

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or…

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Linear attention has emerged as a promising direction for scaling Vision Transformers beyond the quadratic cost of dense self-attention. A prevalent strategy is to compress spatial tokens into a compact set of intermediate proxies that…

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to…

High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint…

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

Employing LLMs for visual generation has recently become a research focus. However, the existing methods primarily transfer the LLM architecture to visual generation but rarely investigate the fundamental differences between language and…

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

Linear attention is an efficient attention mechanism that has recently emerged as a promising alternative to conventional softmax attention. With its ability to process tokens in linear computational complexities, linear attention, in…

Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation under self-supervision.…

This paper presents DetailFlow, a coarse-to-fine 1D autoregressive (AR) image generation method that models images through a novel next-detail prediction strategy. By learning a resolution-aware token sequence supervised with progressively…