English
Related papers

Related papers: LARP: Tokenizing Videos with a Learned Autoregress…

200 papers

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jingfeng Yao , Yuda Song , Yucong Zhou , Xinggang Wang

We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the…

As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital…

Information Retrieval · Computer Science 2024-06-21 Rebecca Salganik , Xiaohao Liu , Yunshan Ma , Jian Kang , Tat-Seng Chua

We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jingyuan Qi , Zhiyang Xu , Qifan Wang , Lifu Huang

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Mao-Lin Luo , Zi-Hao Zhou , Tong Wei , Min-Ling Zhang

Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Zhili Feng , Anna Bair , J. Zico Kolter

We introduce Quantized Language-Image Pretraining (QLIP), a visual tokenization method that combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Yue Zhao , Fuzhao Xue , Scott Reed , Linxi Fan , Yuke Zhu , Jan Kautz , Zhiding Yu , Philipp Krähenbühl , De-An Huang

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

Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Zian Li , Muhan Zhang

We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require…

Remote sensing image-text retrieval plays a crucial role in remote sensing interpretation, yet remains challenging under both closed-domain and open-domain scenarios due to semantic noise and domain shifts. To address these issues, we…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Jiancheng Pan , Muyuan Ma , Qing Ma , Cong Bai , Shengyong Chen

Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid…

Robotics · Computer Science 2026-02-13 Sibaek Lee , Hyeonwoo Yu , Giseop Kim , Sunwook Choi

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually…

Computer Vision and Pattern Recognition · Computer Science 2022-09-05 Xiaodong Chen , Xinchen Liu , Wu Liu , Kun Liu , Dong Wu , Yongdong Zhang , Tao Mei

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Daowen Li , Ruixiao Dong , Ying Chen , Kai Li , Ding Ding , Li Li

Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Hong-Kai Zheng , Piji Li

Autoregressive (AR) language models have emerged as powerful solutions for zero-shot text-to-speech (TTS) synthesis, capable of generating natural speech from a few seconds of audio prompts. However, conventional AR-based TTS systems…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-27 Chun Yat Wu , Jiajun Deng , Guinan Li , Qiuqiang Kong , Simon Lui

Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Divyansh Srivastava , Akshay Mehra , Pranav Maneriker , Debopam Sanyal , Vishnu Raj , Vijay Kamarshi , Fan Du , Joshua Kimball

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Zongcheng Han , Dongyan Cao , Haoran Sun , Yu Hong

Structured pruning is a commonly used convolutional neural network (CNN) compression approach. Pruning rate setting is a fundamental problem in structured pruning. Most existing works introduce too many additional learnable parameters to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Pucheng Zhai , Kailing Guo , Fang Liu , Xiaofen Xing , Xiangmin Xu

Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Anlin Zheng , Haochen Wang , Yucheng Zhao , Weipeng Deng , Tiancai Wang , Xiangyu Zhang , Xiaojuan Qi