Related papers: GigaTok: Scaling Visual Tokenizers to 3 Billion Pa…

With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed…

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…

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual…

Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…

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…

In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understanding and generation. Recently, unified image tokenizers have…

Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides the denoising process from Gaussian noise to the target image…

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…

Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete…

Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencoders like VQGAN or…

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

Image tokenization has significantly advanced visual generation and multimodal modeling, particularly when paired with autoregressive models. However, current methods face challenges in balancing efficiency and fidelity: high-resolution…

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supervision, leading to…

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…

Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper…

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the…

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Autoregressive (AR) image generators offer a language-model-friendly approach to image generation by predicting discrete image tokens in a causal sequence. However, unlike diffusion models, AR models lack a mechanism to refine previous…