Memory as Weights: Internalizing Long-Term History for Streaming Videos
arXiv:2610.22070v1 Announce Type: cross Abstract: Streaming vision-language models (VLMs) must continuously integrate information from the past while remaining responsive to current observations and user queries. Existing memory mechanisms typically compress, retrieve, or cache historical observations and reintroduce them into the input context, forcing historical memory and current observations to compete for limited context. We propose MaLoW, a streaming memory framework that instead internal…