FOLIO: Focused Semantic Memory for Streaming Video Understanding

Jul 16, 2026

Researchers present FOLIO, a training-free semantic memory system for streaming video understanding that selectively retains detailed information about important entities while compressing less relevant context. FOLIO dynamically updates memory as video streams in, combining a short-term visual buffer with a long-term semantic memory organized around entities. The system achieves state-of-the-art results on OVO-Bench and StreamingBench benchmarks, while significantly reducing memory requirements.

Why it matters: This work offers a practical advance in efficient, accurate real-time video understanding by addressing the challenge of long-term memory management in streaming scenarios.

Full story at: arXiv Computer Vision ↗