AI RESEARCH

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

arXiv CS.CV

ArXi:2604.17052v1 Announce Type: new Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert; aggressive compression dries up the oasis. The real difficulty lies in discovering where to look, not how much to remember. We therefore