StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models.

It addresses two fundamental challenges in adapting existing models into online scenarios:

1. limited capability for multi-turn real-time understanding,
2. lack of proactive response mechanisms.

Specifically, StreamBridge incorporates:

1. a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions,
2. a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses.

To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved video-text sequences and diverse instruction formats.

Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1.5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.