English
Related papers

Related papers: StreamPro: From Reactive Perception to Proactive D…

200 papers

We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answering or captioning, Streamo performs a broad spectrum of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Jiaer Xia , Peixian Chen , Mengdan Zhang , Xing Sun , Kaiyang Zhou

Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powered efficient and creative live streaming products but have…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Tianrui Feng , Zhi Li , Shuo Yang , Haocheng Xi , Muyang Li , Xiuyu Li , Lvmin Zhang , Keting Yang , Kelly Peng , Song Han , Maneesh Agrawala , Kurt Keutzer , Akio Kodaira , Chenfeng Xu

Benefiting from the advancements in large language models and cross-modal alignment, existing multi-modal video understanding methods have achieved prominent performance in offline scenario. However, online video streams, as one of the most…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Haoji Zhang , Yiqin Wang , Yansong Tang , Yong Liu , Jiashi Feng , Jifeng Dai , Xiaojie Jin

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Pavan Kumar Anasosalu Vasu , Cem Koc , Fartash Faghri , Chun-Liang Li , Bo Feng , Zhengfeng Lai , Meng Cao , Oncel Tuzel , Hadi Pouransari

Egocentric action anticipation aims to predict the future actions the camera wearer will perform from the observation of the past. While predictions about the future should be available before the predicted events take place, most…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Antonino Furnari , Giovanni Maria Farinella

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…

Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their…

Computation and Language · Computer Science 2024-11-01 Cheng-Kuang Wu , Zhi Rui Tam , Chieh-Yen Lin , Yun-Nung Chen , Hung-yi Lee

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for…

Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimodal personalization methods are largely limited to static…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yuanhong Zheng , Ruichuan An , Xiaopeng Lin , Yuxing Liu , Sihan Yang , Huanyu Zhang , Haodong Li , Qintong Zhang , Renrui Zhang , Guopeng Li , Yifan Zhang , Yuheng Li , Wentao Zhang

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

Computer Vision and Pattern Recognition · Computer Science 2016-04-05 Yu-Chuan Su , Kristen Grauman

Embodied perception refers to the ability of an autonomous agent to perceive its environment so that it can (re)act. The responsiveness of the agent is largely governed by latency of its processing pipeline. While past work has studied the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Mengtian Li , Yu-Xiong Wang , Deva Ramanan

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Vatsal Agarwal , Saksham Suri , Matthew Gwilliam , Pulkit Kumar , Abhinav Shrivastava

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Junming Lin , Zheng Fang , Chi Chen , Zihao Wan , Fuwen Luo , Peng Li , Yang Liu , Maosong Sun

In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over…

Computation and Language · Computer Science 2026-04-07 Pride Kavumba , Koki Wataoka , Huy H. Nguyen , Jiaxuan Li , Masaya Ohagi

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused…

Computer Vision and Pattern Recognition · Computer Science 2021-10-20 Matthias De Lange , Tinne Tuytelaars

In recent years, many works in the video action recognition literature have shown that two stream models (combining spatial and temporal input streams) are necessary for achieving state of the art performance. In this paper we show the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Yinxiao Li , Zhichao Lu , Xuehan Xiong , Jonathan Huang

Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicability in the emerging domain of long-context streaming video…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Zhenyu Yang , Yuhang Hu , Zemin Du , Dizhan Xue , Shengsheng Qian , Jiahong Wu , Fan Yang , Weiming Dong , Changsheng Xu

Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with…

Sound · Computer Science 2025-07-02 Dake Guo , Jixun Yao , Linhan Ma , He Wang , Lei Xie

Predictive queries over spatiotemporal (ST) stream data pose significant data processing and analysis challenges. ST data streams involve a set of time series whose data distributions may vary in space and time, exhibiting multiple distinct…

Machine Learning · Statistics 2024-10-03 Anderson Chaves , Eduardo Ogasawara , Patrick Valduriez , Fabio Porto