Related papers: NativeTok: Native Visual Tokenization for Improved…

Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video…

Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant discrepancy between the reconstruction and generation…

Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize truly novel, out-of-distribution concepts. Existing methods…

Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture,…

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and semantic representations. However, tokenizers constructed on…

The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressive paradigm of large language models. A vision tokenizer trained for reconstruction excels at…

We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new…

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a…

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them…

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual…

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how…

Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…

Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring the variable information density of images and leading to…

Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively…

In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of…

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straightforward modeling…

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…

Recent large-scale vision-language models (VLMs) have shown remarkable text-to-image generation capabilities, yet their visual fidelity remains constrained by the discrete image tokenization, which poses a major challenge. Although several…