FlowNar: Scalable Streaming Narration for Long-Form Videos 事件

FlowNar: Scalable Streaming Narration for Long-Form Videos arXiv:2606.00620v1 Announce Type: new Abstract: Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still face critical scalability challenges, with resource demands typically growing at least linearly with video duration. To overcome this bottleneck, we propose FlowNar, a novel f