Related papers: VA-$\pi$: Variational Policy Alignment for Pixel-A…
We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio:…
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…
Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of…
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…
Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches…
Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a…
Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image…
Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes…
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…
Quantizing images into discrete representations has been a fundamental problem in unified generative modeling. Predominant approaches learn the discrete representation either in a deterministic manner by selecting the best-matching token or…
Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual trial and error to obtain satisfactory results. This motivates the development of…
The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously…
Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that,…
Vision encoders typically generate a large number of visual tokens, providing information-rich representations but significantly increasing computational demands. This raises the question of whether all generated tokens are equally valuable…
Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive…
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…
Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches…
In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder.…
Over the past few years, Text-to-Image (T2I) generation approaches based on diffusion models have gained significant attention. However, vanilla diffusion models often suffer from spelling inaccuracies in the text displayed within the…