English
Related papers

Related papers: VibeToken: Scaling 1D Image Tokenizers and Autoreg…

200 papers

Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and…

Multimedia · Computer Science 2024-07-25 Yongqi Li , Hongru Cai , Wenjie Wang , Leigang Qu , Yinwei Wei , Wenjie Li , Liqiang Nie , Tat-Seng Chua

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Ilia Sudakov , Artem Babenko , Dmitry Baranchuk

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Machine Learning · Computer Science 2025-02-10 Justin Deschenaux , Caglar Gulcehre

Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction fidelity. To fill this gap, we introduce a powerful and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Shaobin Zhuang , Yiwei Guo , Canmiao Fu , Zhipeng Huang , Zeyue Tian , Xiaohui Li , Fangyikang Wang , Ying Zhang , Chen Li , Yali Wang

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Sirine Bhouri , Lan Wei , Jian-Qing Zheng , Dandan Zhang

Autoregressive (AR) language models rely on causal tokenization, but extending this paradigm to vision remains non-trivial. Current visual tokenizers either flatten 2D patches into non-causal sequences or enforce heuristic orderings that…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Yitong Chen , Zuxuan Wu , Xipeng Qiu , Yu-Gang Jiang

Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Yuqing Wang , Shuhuai Ren , Zhijie Lin , Yujin Han , Haoyuan Guo , Zhenheng Yang , Difan Zou , Jiashi Feng , Xihui Liu

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

Computation and Language · Computer Science 2025-10-10 Zhanqiu Hu , Jian Meng , Yash Akhauri , Mohamed S. Abdelfattah , Jae-sun Seo , Zhiru Zhang , Udit Gupta

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Bowen Zheng , Weijian Luo , Guang Yang , Colin Zhang , Tianyang Hu

We introduce ResGen, an efficient Residual Vector Quantization (RVQ)-based generative model for high-fidelity generation with fast sampling. RVQ improves data fidelity by increasing the number of quantization steps, referred to as depth,…

Machine Learning · Computer Science 2025-06-03 Jaehyeon Kim , Taehong Moon , Keon Lee , Jaewoong Cho

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Machine Learning · Computer Science 2025-02-20 Chang Zou , Xuyang Liu , Ting Liu , Siteng Huang , Linfeng Zhang

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Wenda Chu , Bingliang Zhang , Jiaqi Han , Yizhuo Li , Linjie Yang , Yisong Yue , Qiushan Guo

Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yunpeng Qu , Kaidong Zhang , Yukang Ding , Ying Chen , Jian Wang

Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Sucheng Ren , Qihang Yu , Ju He , Xiaohui Shen , Alan Yuille , Liang-Chieh Chen

Semantic image synthesis, i.e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images. Although…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Tariq Berrada , Jakob Verbeek , Camille Couprie , Karteek Alahari

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

Recently, autoregressive (AR) language models have emerged as a dominant approach in speech synthesis, offering expressive generation and scalable training. However, conventional AR speech synthesis models relying on the next-token…

Sound · Computer Science 2025-06-30 Bohan Li , Zhihan Li , Haoran Wang , Hanglei Zhang , Yiwei Guo , Hankun Wang , Xie Chen , Kai Yu

Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean images from ground-truth tokens, while AR generators are optimized only for token…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Xinyao Liao , Qiyuan He , Kai Xu , Xiaoye Qu , Yicong Li , Wei Wei , Angela Yao

Acceleration methods for diffusion models (e.g., token merging or downsampling) typically optimize synthesis quality under reduced compute, yet often ignore discriminative capacity. We revisit token compression with a joint objective and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jiacheng Liu , Shengkun Tang , Jiacheng Cui , Dongkuan Xu , Zhiqiang Shen

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Minglei Shi , Ziyang Yuan , Haotian Yang , Xintao Wang , Mingwu Zheng , Xin Tao , Wenliang Zhao , Wenzhao Zheng , Jie Zhou , Jiwen Lu , Pengfei Wan , Di Zhang , Kun Gai