Related papers: $\bf{D^3}$QE: Learning Discrete Distribution Discr…
Quantization-Aware Training (QAT) is a critical technique for deploying deep neural networks on resource-constrained devices. However, existing methods often face two major challenges: the highly non-uniform distribution of activations and…
We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space.…
While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…
Conventional wisdom holds that autoregressive models for image generation are typically accompanied by vector-quantized tokens. We observe that while a discrete-valued space can facilitate representing a categorical distribution, it is not…
Anomaly detection in images plays a significant role for many applications across all industries, such as disease diagnosis in healthcare or quality assurance in manufacturing. Manual inspection of images, when extended over a monotonously…
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…
Advancements in deep generative models such as generative adversarial networks and variational autoencoders have resulted in the ability to generate realistic images that are visually indistinguishable from real images, which raises…
Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably…
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,…
Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network…
Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and…
Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…
This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a discrete diffusion counterpart, our model achieves…
Generative learning models in medical research are crucial in developing training data for deep learning models and advancing diagnostic tools, but the problem of high-quality, diverse images is an open topic of research. Quantum-enhanced…
Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task. Due to the data scarcity, synthetic data generation has emerged as a…
Generative artificial intelligence holds significant potential for abuse, and generative image detection has become a key focus of research. However, existing methods primarily focused on detecting a specific generative model and…
Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones. This raises concerns about their potential misuse and poses substantial challenges for detecting them. Many existing detectors rely…
Quantum computers could solve problems beyond the reach of classical devices, but this potential depends on quantum error correction (QEC) to protect fragile quantum states from noise. A central challenge in QEC is decoding: inferring…
Recent advances in deep generative models for photo-realistic images have led to high quality visual results. Such models learn to generate data from a given training distribution such that generated images can not be easily distinguished…
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…