Results 201 to 210 of about 75,217 (233)

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

arXiv.org
Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and promising ...
Zhekai Chen, Ruihang Chu, Yukang Chen, Shiwei Zhang, Yujie Wei, Yingya Zhang, Xihui Liu   +6 more
semanticscholar   +1 more source

PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive transformer

International Conference on Computer Graphics and Interactive Techniques
Shape primitive abstraction, which decomposes complex 3D shapes into simple geometric elements, plays a crucial role in human visual cognition and has broad applications in computer vision and graphics. While recent advances in 3D content generation have
Jingwen Ye, Yuze He, Yanning Zhou, Yiqin Zhu, Kaiwen Xiao, Yong-Jin Liu, Wei Yang, Xiao Han   +7 more
semanticscholar   +1 more source

Nested auto-regressive processes for MPEG-encoded video traffic modeling

IEEE Transactions on Circuits and Systems for Video Technology, 2001
This paper presents a new traffic model for MPEG-encoded video sequences. The hybrid gamma/Pareto distribution is used for all three types of frames in MPEG-encoded video sequences, and the present model takes scene changes into account. The autocorrelation structure is modeled using two second-order auto-regressive (AR) processes nested with each ...
null Derong Liu, E.I. Sara, null Wei Sun
openaire   +1 more source

APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding

arXiv.org
The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to achieve efficient serving. In this work,
Mingdao Liu, Aohan Zeng, Bowen Wang, Peng Zhang, Jie Tang, Yuxiao Dong   +5 more
semanticscholar   +1 more source

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Computer Vision and Pattern Recognition
In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency, scalability, and
Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang   +3 more
semanticscholar   +1 more source

Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling

arXiv.org
Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces high processing ...
Haiyang Sun, Shujie Hu, Shujie Liu, Lingwei Meng, Hui Wang, Bing Han, Yifan Yang, Yanqing Liu, Sheng Zhao, Yan Lu, Yanmin Qian   +10 more
semanticscholar   +1 more source

Gaussian Process Auto Regression for vehicle center coordinates Trajectory Prediction

TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), 2019
With the increase in autonomous car technology, and advance driver assistance systems (ADAS), the demand for vehicle trajectory prediction is increasing. These systems mostly use many sensors such as lidar, radar, stereo cameras which are big and expensive to detect the location of the ego vehicles with respect to other vehicles.
Qun Lim, Kritika Johari, U-Xuan Tan
openaire   +1 more source

A Watermark for Auto-Regressive Image Generation Models

arXiv.org
The rapid evolution of image generation models has revolutionized visual content creation, enabling the synthesis of highly realistic and contextually accurate images for diverse applications.
Yihan Wu, Xuehao Cui, Ruibo Chen, Georgios Milis, Heng Huang   +4 more
semanticscholar   +1 more source

Fault detection based on auto-regressive extreme learning machine for nonlinear dynamic processes

Applied Soft Computing, 2021
Abstract Through utilizing the extreme learning machines (ELM) in modeling the nonlinear dynamic relationship of the time-series data, a novel fault detection approach based on auto-regressive ELM (ARELM) is proposed for nonlinear dynamic processes.
Yang Chen, Chudong Tong, Yinghui Ge, Ting Lan   +3 more
openaire   +1 more source

Dual auto-regressive modelling approach to Gaussian process identification

IEEE International Conference on Multimedia and Expo, 2001. ICME 2001., 2001
By modelling sources as a multivariate auto-regressive (AR) process, we have recently presented a dual AR modelling approach to identify temporal sources in independent component analysis (ICA) (Cheung et al. 2000, Cheung and Xu 1999 & 2001). However, our proposed existing algorithms for this approach are only suitable for the case that the residual ...
openaire   +1 more source