中文
相关论文

相关论文: D2C: Unlocking the Potential of Continuous Autoreg…

200 篇论文

Autoregressive visual generation models typically rely on tokenizers to compress images into tokens that can be predicted sequentially. A fundamental dilemma exists in token representation: discrete tokens enable straightforward modeling…

计算机视觉与模式识别 · 计算机科学 2025-09-01 Yuqing Wang , Zhijie Lin , Yao Teng , Yuanzhi Zhu , Shuhuai Ren , Jiashi Feng , Xihui Liu

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire. This paper describes Diffusion-Decoding models with Contrastive representations…

机器学习 · 计算机科学 2021-06-15 Abhishek Sinha , Jiaming Song , Chenlin Meng , Stefano Ermon

Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…

计算机视觉与模式识别 · 计算机科学 2025-01-31 Yinbo Chen , Rohit Girdhar , Xiaolong Wang , Sai Saketh Rambhatla , Ishan Misra

Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Ze Wang , Hao Chen , Benran Hu , Jiang Liu , Ximeng Sun , Jialian Wu , Yusheng Su , Xiaodong Yu , Emad Barsoum , Zicheng Liu

This paper presents Diffusion via Autoregressive models (D-AR), a new paradigm recasting the image diffusion process as a vanilla autoregressive procedure in the standard next-token-prediction fashion. We start by designing the tokenizer…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Ziteng Gao , Mike Zheng Shou

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Chuhan Wang , Hao Chen

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Peng Zheng , Junke Wang , Yi Chang , Yizhou Yu , Rui Ma , Zuxuan Wu

Diffusion models have achieved remarkable performance on a wide range of generative tasks, yet training them from scratch is notoriously resource-intensive, typically requiring millions of training images and many GPU days. Motivated by a…

机器学习 · 计算机科学 2026-03-16 Rui Huang , Shitong Shao , Zikai Zhou , Pukun Zhao , Hangyu Guo , Tian Ye , Lichen Bai , Shuo Yang , Zeke Xie

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…

计算机视觉与模式识别 · 计算机科学 2024-11-04 Tianhong Li , Yonglong Tian , He Li , Mingyang Deng , Kaiming He

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Wenda Chu , Bingliang Zhang , Jiaqi Han , Yizhuo Li , Linjie Yang , Yisong Yue , Qiushan Guo

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational…

计算机视觉与模式识别 · 计算机科学 2024-06-12 Qihang Yu , Mark Weber , Xueqing Deng , Xiaohui Shen , Daniel Cremers , Liang-Chieh Chen

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

计算机视觉与模式识别 · 计算机科学 2026-01-23 Theodoros Kouzelis , Efstathios Karypidis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding diversity. Inspired…

计算机视觉与模式识别 · 计算机科学 2023-05-23 Yufeng He , Zefan Cai , Xu Gan , Baobao Chang

Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve the…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Xiang Li , Kai Qiu , Hao Chen , Jason Kuen , Jiuxiang Gu , Bhiksha Raj , Zhe Lin

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Erik Riise , Mehmet Onurcan Kaya , Dim P. Papadopoulos

In recent years, significant progress has been made in the development of text-to-image generation models. However, these models still face limitations when it comes to achieving full controllability during the generation process. Often,…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Salaheldin Mohamed

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Idan Schwartz , Vésteinn Snæbjarnarson , Hila Chefer , Ryan Cotterell , Serge Belongie , Lior Wolf , Sagie Benaim

Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Zhihang Yuan , Yuzhang Shang , Hanling Zhang , Tongcheng Fang , Rui Xie , Bingxin Xu , Yan Yan , Shengen Yan , Guohao Dai , Yu Wang

Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Chongbin Yi , Yuxin Liang , Ziqi Zhou , Peng Yang

Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost…

‹ 上一页 1 2 3 10 下一页 ›