相关论文: Scale-Wise VAR is Secretly Discrete Diffusion

We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of…

Understanding the expressive ability of a specific model is essential for grasping its capacity limitations. Recently, several studies have established circuit complexity bounds for Transformer architecture. Besides, the Visual…

Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation…

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…

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…

The rapid progress of large multimodal models has inspired efforts toward unified frameworks that couple understanding and generation. While such paradigms have shown remarkable success in 2D, extending them to 3D remains largely…

In generative models, two paradigms have gained attraction in various applications: next-set prediction-based Masked Generative Models and next-noise prediction-based Non-Autoregressive Models, e.g., Diffusion Models. In this work, we…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

In the visual generative area, discrete diffusion models are gaining traction for their efficiency and compatibility. However, pioneered attempts still fall behind their continuous counterparts, which we attribute to noise (absorbing state)…

Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and…

Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong…

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Diffusion models have established themselves as state-of-the-art generative models across various data modalities, including images and videos, due to their ability to accurately approximate complex data distributions. Unlike traditional…

Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying…

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive…

Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for…

Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is…

Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as generating random…