相关论文: Adapting Self-Supervised Representations as a Late…

We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By employing an InfoGAN-style objective, where we train a…

Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large…

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…

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…

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…

Real-time transmission of video over wireless networks remains highly challenging, even with advanced deep models, particularly under severe channel conditions such as limited bandwidth and weak connectivity. In this paper, we propose…

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…

Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer:…

Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and…

This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we…

Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction fidelity. To fill this gap, we introduce a powerful and…

Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain…

Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies…

In the majority of GAN architectures, the latent space is defined as a set of vectors of given dimensionality. Such representations are not easily interpretable and do not capture spatial information of image content directly. In this work,…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation…

Generative linguistic steganography (GLS) enables covert communication by embedding secret messages into the natural language generation process. In practical deployment, however, GLS is vulnerable to tokenization ambiguity: the same…

This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTok), a novel video tokenizer to overcome the limitations in current video tokenization methods for compacted yet effective…

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…

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…