Related papers: Factorized Visual Tokenization and Generation

Audio tokenization has emerged as a critical component in end-to-end audio language models, enabling efficient discrete representation learning for both audio understanding and generation tasks. However, existing audio tokenizers face…

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider…

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…

Foundation models in language and vision benefit from a unified discrete token interface that converts raw inputs into sequences for scalable pre-training and inference. For graphs, an effective tokenizer should yield reusable discrete…

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following…

Vector quantization(VQ) is a lossy data compression technique from signal processing for which simple competitive learning is one standard method to quantize patterns from the input space. Extending competitive learning VQ to the domain of…

Generating emotional talking faces is a practical yet challenging endeavor. To create a lifelike avatar, we draw upon two critical insights from a human perspective: 1) The connection between audio and the non-deterministic facial dynamics,…

Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived…

Recent advances in auto-regressive transformers have achieved remarkable success in generative modeling. However, text-to-3D generation remains challenging, primarily due to bottlenecks in learning discrete 3D representations. Specifically,…

We introduce FewGAN, a generative model for generating novel, high-quality and diverse images whose patch distribution lies in the joint patch distribution of a small number of N>1 training samples. The method is, in essence, a hierarchical…

The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via…

In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting…

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…

Over the last decades, hand-crafted feature extractors have been used to encode image visual properties into feature vectors. Recently, data-driven feature learning approaches have been successfully explored as alternatives for producing…

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component…

Vector Quantisation (VQ) is experiencing a comeback in machine learning, where it is increasingly used in representation learning. However, optimizing the codevectors in existing VQ-VAE is not entirely trivial. A problem is codebook…

Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such…

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Medical image synthesis is crucial for alleviating data scarcity and privacy constraints. However, fine-tuning general text-to-image (T2I) models remains challenging, mainly due to the significant modality gap between complex visual details…

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…