SOURCE-LINKED INTELLIGENCE

StreamScout: Learning When to Look Deeper for Streaming Video Understanding

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily focus on what to retain in a bounded memory, yet access that memory using the same fixed-cost procedure for every query, despite substantial variation in the evidence required. We argue that deciding how deeply to access memory for each query is as important as deciding what the memory should store. To this end, we introduce StreamScout, an adaptive inference framework that maintains only a lightweight textual timeline in context as the stream u

Read original source ↗ Open in workspace

recordType

paper

region

Global