English
Related papers

Related papers: Learning Adaptive and Temporally Causal Video Toke…

200 papers

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Bowei Chen , Sai Bi , Hao Tan , He Zhang , Tianyuan Zhang , Zhengqi Li , Yuanjun Xiong , Jianming Zhang , Kai Zhang

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Ayush K. Rai , Kyle Min , Tarun Krishna , Feiyan Hu , Alan F. Smeaton , Noel E. O'Connor

Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haifeng Huang , Yang Li

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Jiasen Lu , Liangchen Song , Mingze Xu , Byeongjoo Ahn , Yanjun Wang , Chen Chen , Afshin Dehghan , Yinfei Yang

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive…

Computation and Language · Computer Science 2023-11-14 Siyang Liu , Naihao Deng , Sahand Sabour , Yilin Jia , Minlie Huang , Rada Mihalcea

Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Zanlin Ni , Yulin Wang , Yeguo Hua , Renping Zhou , Jiayi Guo , Jun Song , Bo Zheng , Gao Huang

Humans have the ability to adapt the type of information they use, the procedure they employ, and the amount of time they spend when solving problems. However, most standard neural networks have a fixed function type and computation budget…

Machine Learning · Computer Science 2023-06-06 Fuzhao Xue , Valerii Likhosherstov , Anurag Arnab , Neil Houlsby , Mostafa Dehghani , Yang You

Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Zhaoyang Liu , Limin Wang , Wayne Wu , Chen Qian , Tong Lu

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Jianwei Yang , Yonatan Bisk , Jianfeng Gao

Spatial convolutions are extensively used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Ziyuan Huang , Shiwei Zhang , Liang Pan , Zhiwu Qing , Yingya Zhang , Ziwei Liu , Marcelo H. Ang

Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Hengyu Zeng , Xin Gao , Guanghao Li , Yuxiang Yan , Jiaoyang Ruan , Junpeng Ma , Haoyu Albert Wang , Jian Pu

Visuomotor policies often suffer from perceptual challenges, where visual differences between training and evaluation environments degrade policy performance. Policies relying on state estimations, like 6D pose, require task-specific…

Robotics · Computer Science 2025-10-07 Yunchu Zhang , Shubham Mittal , Zhengyu Zhang , Liyiming Ke , Siddhartha Srinivasa , Abhishek Gupta

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Tianxiong Zhong , Xingye Tian , Boyuan Jiang , Xuebo Wang , Xin Tao , Pengfei Wan , Zhiwei Zhang

Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most video diffusion models (VDMs) generate videos in an…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Tianle Cheng , Zeyan Zhang , Kaifeng Gao , Jun Xiao

Existing speech tokenizers typically assign a fixed number of tokens per second, regardless of the varying information density or temporal fluctuations in the speech signal. This uniform token allocation mismatches the intrinsic structure…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-14 Rui-Chen Zheng , Wenrui Liu , Hui-Peng Du , Qinglin Zhang , Chong Deng , Qian Chen , Wen Wang , Yang Ai , Zhen-Hua Ling

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yizhuo Li , Yuying Ge , Yixiao Ge , Ying Shan , Ping Luo

Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 Ziyuan Huang , Shiwei Zhang , Liang Pan , Zhiwu Qing , Mingqian Tang , Ziwei Liu , Marcelo H. Ang

Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yinchao Ma , Qiang Zhou , Zhibin Wang , Xianing Chen , Hanqing Yang , Jun Song , Bo Zheng

Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shida Wang , YongXiang Hua , Zhou Tao , Haoyu Cao , Linli Xu

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Tianwei Xiong , Jun Hao Liew , Zilong Huang , Jiashi Feng , Xihui Liu