Paper Detail
Xudong Lu, Yang Bo, Jinpeng Chen, Shuhan Li, Xintong Guo, Huankang Guan, Fang Liu, Dunyuan Xu, Peiwen Sun, Heyang Sun, Rui Liu, Hongsheng Li
Video Large Language Models (VideoLLMs) have achieved strong performance on many video understanding tasks, but most existing systems remain offline and are not well-suited for live video streams that require continuous observation and timely response. Recent streaming VideoLLMs have made progress, yet current approaches often rely on decoupled trigger-response pipelines or are limited to captioning-style narration, reducing their effectiveness for open-ended question answering and long-horizon interaction. We propose AURA (Always-On Understanding and Real-Time Assistance), an end-to-end streaming visual interaction framework that enables a unified VideoLLM to continuously process video streams and support both real-time question answering and proactive responses. AURA integrates context management, data construction, training objectives, and deployment optimization for stable long-horizon streaming interaction. It achieves state-of-the-art performance on streaming benchmarks and supports a real-time demo system with ASR and TTS running at 2 FPS on two 80G accelerators. We release the AURA model together with a real-time inference framework to facilitate future research.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{lu2026aura,
title = {AURA: Always-On Understanding and Real-Time Assistance via Video Streams},
author = {Xudong Lu and Yang Bo and Jinpeng Chen and Shuhan Li and Xintong Guo and Huankang Guan and Fang Liu and Dunyuan Xu and Peiwen Sun and Heyang Sun and Rui Liu and Hongsheng Li},
year = {2026},
abstract = {Video Large Language Models (VideoLLMs) have achieved strong performance on many video understanding tasks, but most existing systems remain offline and are not well-suited for live video streams that require continuous observation and timely response. Recent streaming VideoLLMs have made progress, yet current approaches often rely on decoupled trigger-response pipelines or are limited to captioning-style narration, reducing their effectiveness for open-ended question answering and long-horizon },
url = {https://huggingface.co/papers/2604.04184},
keywords = {VideoLLMs, streaming VideoLLMs, real-time question answering, proactive responses, context management, data construction, training objectives, deployment optimization, long-horizon streaming interaction, ASR, TTS, code available, huggingface daily},
eprint = {2604.04184},
archiveprefix = {arXiv},
}
{}