Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
- 类型：arxiv
- 标识：2609.04131
- 链接：https://arxiv.org/abs/2609.04131
- 主分类：rag
- 形态：method
- TLDR：Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-relevant evidence as additional visual context. Though effective, this store-and-retrieve paradigm keeps historical evidence as external visual context, preventing it from being internalized into a compact, evolving latent memory that can continuously guide streaming reasoning. To bridge this gap, we
- 副分类：multimodal
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-04-agent-rag-longcontext-candidates.json