English
Related papers

Related papers: StreamWise: Serving Multi-Modal Generation in Real…

200 papers

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Yi Wei , Shunpu Tang , Liang Zhao , Qiangian Yang

3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices,…

Graphics · Computer Science 2025-06-12 Chenqi Zhang , Yu Feng , Jieru Zhao , Guangda Liu , Wenchao Ding , Chentao Wu , Minyi Guo

StreamVoice has recently pushed the boundaries of zero-shot voice conversion (VC) in the streaming domain. It uses a streamable language model (LM) with a context-aware approach to convert semantic features from automatic speech recognition…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-06 Zhichao Wang , Yuanzhe Chen , Xinsheng Wang , Lei Xie , Yuping Wang

With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a…

Networking and Internet Architecture · Computer Science 2025-05-30 Jiangkai Wu , Liming Liu , Yunpeng Tan , Junlin Hao , Xinggong Zhang

Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-05 Yuchen Xia , Divyam Sharma , Yichao Yuan , Souvik Kundu , Nishil Talati

Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA inevitably loses distant history during long video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ruibin Li , Tao Yang , Fangzhou Ai , Tianhe Wu , Shilei Wen , Bingyue Peng , Lei Zhang

Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-window baseline that feeds only the most recent N frames to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yujiao Shen , Shulin Tian , Jingkang Yang , Ziwei Liu

Live animation has gained immense popularity for enhancing online engagement, yet achieving high-quality, real-time, and stable animation with diffusion models remains challenging, especially on consumer-grade GPUs. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Zhilei Shu , Ruili Feng , Yang Cao , Zheng-Jun Zha

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly…

Machine Learning · Computer Science 2026-02-03 Keisuke Kamahori , Wei-Tzu Lee , Atindra Jha , Rohan Kadekodi , Stephanie Wang , Arvind Krishnamurthy , Baris Kasikci

Live-streaming Novel View Synthesis (NVS) from unposed multi-view video remains an open challenge in a wide range of applications. Existing methods for dynamic scene representation typically require ground-truth camera parameters and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Pedro Quesado , Erkut Akdag , Yasaman Kashefbahrami , Willem Menu , Egor Bondarev

This paper proposes StreamCodec, a streamable neural audio codec designed for real-time communication. StreamCodec adopts a fully causal, symmetric encoder-decoder structure and operates in the modified discrete cosine transform (MDCT)…

Sound · Computer Science 2025-04-10 Xiao-Hang Jiang , Yang Ai , Rui-Chen Zheng , Zhen-Hua Ling

Streaming analysis is widely used in cloud as well as edge infrastructures. In these contexts, fine-grained application performance can be based on accurate modeling of streaming operators. This is especially beneficial for computationally…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-11-30 Hannaneh Najdataei , Vincenzo Gulisano , Alessandro V. Papadopoulos , Ivan Walulya , Marina Papatriantafilou , Philippas Tsigas

Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is challenging due to their high computational cost, particularly at…

Machine Learning · Computer Science 2026-01-19 Runyu Lu , Shiqi He , Wenxuan Tan , Shenggui Li , Ruofan Wu , Jeff J. Ma , Ang Chen , Mosharaf Chowdhury

Stream-reasoning query languages such as CQELS and C-SPARQL enable query answering over RDF streams. Unfortunately, there currently is a lack of efficient RDF stream generators to feed RDF stream reasoners. State-of-the-art RDF stream…

Databases · Computer Science 2022-10-27 Sitt Min Oo , Gerald Haesendonck , Ben De Meester , Anastasia Dimou

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

Computation and Language · Computer Science 2020-11-17 Ching-Feng Yeh , Yongqiang Wang , Yangyang Shi , Chunyang Wu , Frank Zhang , Julian Chan , Michael L. Seltzer

Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from…

Sound · Computer Science 2025-09-05 Kun Xie , Feiyu Shen , Junjie Li , Fenglong Xie , Xu Tang , Yao Hu

Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long inference latency, which largely…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Long Zhuo , Guangcong Wang , Shikai Li , Wayne Wu , Ziwei Liu

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Ming Chen , Liyuan Cui , Wenyuan Zhang , Haoxian Zhang , Yan Zhou , Xiaohan Li , Songlin Tang , Jiwen Liu , Borui Liao , Hejia Chen , Xiaoqiang Liu , Pengfei Wan

The integration of generative AI models, particularly large language models (LLMs), into real-time multi-model AI applications such as video conferencing and gaming is giving rise to a new class of workloads: real-time generative AI…

Machine Learning · Computer Science 2025-07-22 Rachid Karami , Rajeev Patwari , Hyoukjun Kwon , Ashish Sirasao