OneStreamer unifies perception, memory, and timely response in streaming video through a shared proactive generation interface, with a 4B model achieving the best results among compared methods across eight streaming video understanding benchmarks
OneStreamer jointly learns query-independent evidence recording and task response through a shared proactive generation process: its Proactive Hierarchical Caption Memory produces time-grounded local-detail captions and summaries of completed events, Proactive State Transition Learning outperforms dense state supervision while supervising only 27.5% of annotated state tokens, a streaming data synthesis pipeline yields the OneStreamer-1M dataset with over one million records, and the 4B model achieves the best results among compared methods across all eight evaluated streaming video understanding benchmarks, with ablations showing that retaining generated captions improves historical QA without degrading real-time perception.