AI RESEARCH
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management
arXiv CS.CV
•
ArXi:2603.19571v1 Announce Type: new Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explosion of visual tokens, which often leads to Out-of-Memory (OOM) errors or catastrophic forgetting. Existing visual retention and memory management methods typically rely on uniform sampling, low-level physical metrics, or passive cache eviction.