English
Related papers

Related papers: Network-Efficient World Model Token Streaming

200 papers

Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input…

Machine Learning · Computer Science 2026-02-11 Saurish Nagrath , Saroj Kumar Panigrahy

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Serin Varghese , Kevin Ross , Fabian Hueger , Kira Maag

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Akash Haridas , Utkarsh Saxena , Parsa Ashrafi Fashi , Mehdi Rezagholizadeh , Vikram Appia , Emad Barsoum

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Huaibo Huang , Xiaoqiang Zhou , Jie Cao , Ran He , Tieniu Tan

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Computation and Language · Computer Science 2025-06-12 Darius Feher , Ivan Vulić , Benjamin Minixhofer

Rate control is widely adopted during video streaming to provide both high video qualities and low latency under various network conditions. However, despite that many work have been proposed, they fail to tackle one major problem: previous…

Multimedia · Computer Science 2018-10-29 Tianchi Huang , Rui-Xiao Zhang , Chao Zhou , Lifeng Sun

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Machine Learning · Computer Science 2025-10-06 Junyi Chen , Chuheng Du , Renyuan Liu , Shuochao Yao , Dingtian Yan , Jiang Liao , Shengzhong Liu , Fan Wu , Guihai Chen

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-05 Chengyi Wang , Yu Wu , Shujie Liu , Jinyu Li , Liang Lu , Guoli Ye , Ming Zhou

Many machine learning algorithms have been developed under the assumption that data sets are already available in batch form. Yet in many application domains data is only available sequentially overtime via compute nodes in different…

Optimization and Control · Mathematics 2020-09-10 Alfredo Garcia , Luochao Wang , Jeff Huang , Lingzhou Hong

We present data streaming algorithms for the $k$-median problem in high-dimensional dynamic geometric data streams, i.e. streams allowing both insertions and deletions of points from a discrete Euclidean space $\{1, 2, \ldots \Delta\}^d$.…

Data Structures and Algorithms · Computer Science 2017-06-14 Vladimir Braverman , Gereon Frahling , Harry Lang , Christian Sohler , Lin F. Yang

Real-time video surveillance has become a crucial technology for smart cities, made possible through the large-scale deployment of mobile and fixed video cameras. In this paper, we propose situation-aware streaming, for real-time…

Networking and Internet Architecture · Computer Science 2022-04-06 Suvadip Batabyal , Ozgur Ercetin

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Xinhao Zhong , Shuoyang Sun , Xulin Gu , Zhaoyang Xu , Yaowei Wang , Min Zhang , Bin Chen

Video stabilization often struggles with distortion and excessive cropping. This paper proposes a novel end-to-end framework, named TranStable, to address these challenges, comprising a genera tor and a discriminator. We establish…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 zhizhen li , tianyi zhuo , Yifei Cao , Jizhe Yu , Yu Liu

In recent years, studying and predicting alternative mobility (e.g., sharing services) patterns in urban environments has become increasingly important as accurate and timely information on current and future vehicle flows can successfully…

Machine Learning · Computer Science 2021-08-19 Stefano Fiorini , Michele Ciavotta , Andrea Maurino

Training large and highly accurate deep learning (DL) models is computationally costly. This cost is in great part due to the excessive number of trained parameters, which are well-known to be redundant and compressible for the execution…

Machine Learning · Computer Science 2019-04-11 Mojan Javaheripi , Bita Darvish Rouhani , Farinaz Koushanfar

Distributed deep learning (DDL) training systems are designed for cloud and data-center environments that assumes homogeneous compute resources, high network bandwidth, sufficient memory and storage, as well as independent and identically…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-01-30 Sahil Tyagi , Martin Swany

We introduce a novel network-adaptive algorithm that is suitable for alleviating network packet losses for low-latency interactive communications between a source and a destination. Our network-adaptive algorithm estimates in real-time the…

Networking and Internet Architecture · Computer Science 2020-06-30 Salma Emara , Silas L. Fong , Baochun Li , Ashish Khisti , Wai-Tian Tan , Xiaoqing Zhu , John Apostolopoulos

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Jing Wang , Ao Ma , Jiasong Feng , Dawei Leng , Yuhui Yin , Xiaodan Liang

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Min Shi , Shihao Wang , Chieh-Yun Chen , Jitesh Jain , Kai Wang , Junjun Xiong , Guilin Liu , Zhiding Yu , Humphrey Shi

This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Wenqiang Sun , Haiyu Zhang , Haoyuan Wang , Junta Wu , Zehan Wang , Zhenwei Wang , Yunhong Wang , Jun Zhang , Tengfei Wang , Chunchao Guo