Related papers: VA-$\pi$: Variational Policy Alignment for Pixel-A…

The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation. To address this issue, this paper proposes Direction-Aware…

Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time, making them vulnerable to exposure bias and prefix drift. Existing remedies either…

Vision Language Models (VLMs) are increasingly used for detecting AI-generated images (AIGI). However, converting VLMs into reliable detectors is resource-intensive, and the resulting models often suffer from hallucination and poor…

Autoregressive (AR) models have demonstrated significant success in the realm of text-to-image generation. However, they usually face two major challenges. Firstly, the generated images may not always meet the quality standards expected by…

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework…

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic…

Test-time scaling (TTS) has demonstrated remarkable success in enhancing large language models, yet its application to next-token prediction (NTP) autoregressive (AR) image generation remains largely uncharted. Existing TTS approaches for…

We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refreshable vision-language prefixes. In contrast to existing Vision-Language-Action (VLA) models and…

Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works extended GANs to image inpainting by conditioning the generation with parts of the image one wants to reconstruct. However, these…

We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the…

Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation tasks. While conditional generation has been widely…

Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works have extended GANs to image inpainting by conditioning the generation with parts of the image to be reconstructed. Despite their…

In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unlabeled videos. Previous methods are mainly based on the…

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through…

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a labeled dataset in a supervised fashion, we augment our…

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…

Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging…

Autoregressive models recently achieved comparable results versus state-of-the-art Generative Adversarial Networks (GANs) with the help of Vector Quantized Variational AutoEncoders (VQ-VAE). However, autoregressive models have several…