BLIP-Live unifies data, metrics, inference, and training for proactive streaming video understanding, using the PAUC-F metric and achieving state-of-the-art results on proactive streaming benchmarks.
Streaming video understanding is becoming increasingly important for real-world interactive systems. Such systems must be proactive for natural and useful human interaction: they should respond as soon as sufficient evidence becomes available while avoiding premature, redundant, or incorrect responses. We present BLIP-Live, a framework unifying data, metrics, harness, and training around a shared formulation of proactivity as effective causal response decisions balancing the two competing objectives of responding vs silence. First, we construct BLIP-Live-780K dataset containing human annotations of proactive response content and timing, which defines this desired behavior. We then propose…
streaming video understandingproactive responsecausal response decisionsvision language modelsVLMsinference harnessestraining pipelinessliding visual windowsonline interaction memorystructured response outputs
- Upvotes
- 5
- Authors
- 8
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.