相关论文: Exploiting Discriminative Codebook Prior for Autor…

We present a novel generative approach based on Denoising Diffusion Models (DDMs), which produces high-quality image samples along with their losslessly compressed bit-stream representations. This is obtained by replacing the standard…

Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…

Conditional discrete generative models struggle to faithfully compose multiple input conditions. To address this, we derive a theoretically-grounded formulation for composing discrete probabilistic generative processes, with masked…

This paper presents an innovative enhancement to the Sphere as Prior Generative Adversarial Network (SP-GAN) model, a state-of-the-art GAN designed for point cloud generation. A novel method is introduced for point cloud generation that…

Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to the point cloud domain. Nevertheless, existing point cloud…

In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative…

Autoregressive image generation has witnessed rapid advancements, with prominent models such as scale-wise visual auto-regression pushing the boundaries of visual synthesis. However, these developments also raise significant concerns…

Unsupervised fine-grained class clustering is a practical yet challenging task due to the difficulty of feature representations learning of subtle object details. We introduce C3-GAN, a method that leverages the categorical inference power…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the…

Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To…

Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG). However, vanilla prompt tuning tends to imitate training corpus characteristics beyond the control…

Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the…

Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis, but they suffer from high computational cost. We study how to design compute-efficient linear…

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through…

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

In standard autoregressive generation, an LLM predicts the next-token distribution, samples a discrete token, and then discards the distribution, passing only the sampled token as new input. To preserve this distribution's rich information,…

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we develop the first…

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to…