English
Related papers

Related papers: Depth Adaptive Efficient Visual Autoregressive Mod…

200 papers

Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-scale sequence of dense image tokens, and is incapable of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Guangting Zheng , Yehao Li , Yingwei Pan , Jiajun Deng , Ting Yao , Yanyong Zhang , Tao Mei

The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers). Our work is…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yulin Wang , Yang Yue , Rui Lu , Tianjiao Liu , Zhao Zhong , Shiji Song , Gao Huang

Remote sensing change detection aims to localize and characterize scene changes between two time points and is central to applications such as environmental monitoring and disaster assessment. Meanwhile, visual autoregressive models (VARs)…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Yilmaz Korkmaz , Vishal M. Patel

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Hao Yu , Jianxin Wu

Variational data assimilation estimates the dynamical system states by minimizing a cost function that fits the numerical models with the observational data. Although four-dimensional variational assimilation (4D-Var) is widely used, it…

Machine Learning · Computer Science 2025-06-16 Yiming Yang , Xiaoyuan Cheng , Daniel Giles , Sibo Cheng , Yi He , Xiao Xue , Boli Chen , Yukun Hu

We develop a Bayesian vector autoregressive (VAR) model with multivariate stochastic volatility that is capable of handling vast dimensional information sets. Three features are introduced to permit reliable estimation of the model. First,…

Computation · Statistics 2020-03-12 Gregor Kastner , Florian Huber

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Machine Learning · Computer Science 2024-12-19 Bartosz Wójcik , Alessio Devoto , Karol Pustelnik , Pasquale Minervini , Simone Scardapane

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Ling Li , David Thorsley , Joseph Hassoun

Vision-Language Models (VLMs) have achieved notable success in multimodal tasks but face practical limitations due to the quadratic complexity of decoder attention mechanisms and autoregressive generation. Existing methods like FASTV and…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Xiaoyu Liang , Chaofeng Guan , Jiaying Lu , Huiyao Chen , Huan Wang , Haoji Hu

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

The objective of transfer learning is to enhance estimation and inference in a target data by leveraging knowledge gained from additional sources. Recent studies have explored transfer learning for independent observations in complex,…

Machine Learning · Statistics 2025-04-23 Mingliang Ma Abolfazl Safikhani

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Putu Indah Githa Cahyani , Komang David Dananjaya Suartana , Novanto Yudistira

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Hongxu Yin , Arash Vahdat , Jose Alvarez , Arun Mallya , Jan Kautz , Pavlo Molchanov

Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Daxin Li , Yuanchao Bai , Kai Wang , Wenbo Zhao , Junjun Jiang , Xianming Liu

Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for transforming degraded features into clean ones in image…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Siyang Wang , Feng Zhao

The standard vector autoregressive (VAR) models suffer from overparameterization which is a serious issue for high-dimensional time series data as it restricts the number of variables and lags that can be incorporated into the model.…

Methodology · Statistics 2023-09-25 S. Yaser Samadi , Wiranthe B. Herath

Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area has been largely…

Machine Learning · Computer Science 2026-03-24 Yi-Chung Chen , David I. Inouye , Jing Gao

Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capability, existing VAR-based personalization methods remain limited to static settings,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Junhao Li , Xinhao Zhong , Yi sun , Yuxia Qiao , Bin Chen , Shu-Tao Xia , Yaowei Wang

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

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Computation and Language · Computer Science 2020-12-17 Yijin Liu , Fandong Meng , Jie Zhou , Yufeng Chen , Jinan Xu