相关论文: A Spark of Vision-Language Intelligence: 2-Dimensi…

This survey explores the adaptation of visual transformer models in Autonomous Driving, a transition inspired by their success in Natural Language Processing. Surpassing traditional Recurrent Neural Networks in tasks like sequential image…

An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high…

Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image…

Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly…

Large transformer-based models have made significant progress in generalizable novel view synthesis (NVS) from sparse input views, generating novel viewpoints without the need for test-time optimization. However, these models are…

Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a…

Neuron reconstruction, one of the fundamental tasks in neuroscience, rebuilds neuronal morphology from 3D light microscope imaging data. It plays a critical role in analyzing the structure-function relationship of neurons in the nervous…

Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective…

There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to…

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional…

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual…

Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the…

We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of…

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…

Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction…

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a…