Related papers: ENAT: Rethinking Spatial-temporal Interactions in …

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…

Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously. Despite its high efficiency, NAT usually suffers from two kinds of translation errors: over-translation…

Generative Adversarial Networks (GANs) have emerged as a significant player in generative modeling by mapping lower-dimensional random noise to higher-dimensional spaces. These networks have been used to generate high-resolution images and…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Simulating interactions between deformable bodies is vital in fields like material science, mechanical design, and robotics. While learning-based methods with Graph Neural Networks (GNNs) are effective at solving complex physical systems,…

Representing a dynamic scene using a structured spatial-temporal scene graph is a novel and particularly challenging task. To tackle this task, it is crucial to learn the temporal interactions between objects in addition to their spatial…

Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token…

A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work. Although automatic synthesis of visually pleasant texture can be achieved by deep neural networks nowadays, the associated…

State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce…

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger…

Data-driven and deep learning approaches have demonstrated to have the potential of replacing classical constitutive models for complex materials. Yet, the necessity of structuring constitutive models with an incremental formulation has…

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where…

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

Transformer-based autoregressive models offer an efficient alternative to diffusion- and flow-matching-based approaches for generating 3D molecules. One challenge remains: standard transformer architectures require a sequential ordering of…

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual…

State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can generate high-quality videos, it suffers from slow convergence…

We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic…

Synthetic data generation to improve classification performance (data augmentation) is a well-studied problem. Recently, generative adversarial networks (GAN) have shown superior image data augmentation performance, but their suitability in…

Electrical tomography techniques have been widely employed for multiphase-flow monitoring owing to their non invasive nature, intrinsic safety, and low cost. Nevertheless, conventional reconstructions struggle to capture fine details, which…

Achieving precise camera control in video generation remains challenging, as existing methods often rely on camera pose annotations that are difficult to scale to large and dynamic datasets and are frequently inconsistent with depth…