StreamFlow: Dynamic Memory Flows for Streaming Video Understanding

• URL: http://arxiv.org/abs/2608.10949v1
• Date: Tue, 11 Aug 2026 14:19:03 GMT
• Title: StreamFlow: Dynamic Memory Flows for Streaming Video Understanding
• Abstract summary: StreamFlow is an efficient visual memory framework that enables dynamic, on-demand access to historical visual information.<n>It achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench.<n>Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively.
• Score: 65.10324190760602
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality and bounded memory. Yet existing paradigms remain limited: model-based methods require intrusive backbone updates, while memory-based methods expend substantial visual-encoding computation on temporally redundant content and rely on rigid access to visual history. To address these limitations, we introduce StreamFlow, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information. StreamFlow combines a lightweight, dynamics-aware mid-term memory that filters temporal redundancy before visual encoding with a latent long-term memory that consolidates historical video content into visual latents accessible to subsequent reasoning. During generation, an attention-guided retrieval mechanism injects relevant visual latents when the model's reliance on visual evidence weakens. StreamFlow achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench, while also delivering strong performance on offline long-video benchmarks. Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively, enabling more visually grounded and efficient reasoning.

Related papers

• Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding [64.34948094316685]
  We introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize.<n>LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T17:28:14Z)
• ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding [50.17161313335395]
  ObjectStream is a training-free framework that treats latent objects as memory anchors for streaming video understanding.<n>It preserves three complementary forms of evidence: persistent object histories, transient object changes, and recent visual context.<n>Experiments on online streaming and offline long-video benchmarks demonstrate both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-07-30T14:47:00Z)
• FOLIO: Focused Semantic Memory for Streaming Video Understanding [7.067883491096352]
  In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time.<n>As this history grows with the stream, memory cost increases and many redundant visual details are retained.<n>We introduce FOLIO, a training-free focused semantic memory system that records important parts of the stream in higher detail.
  arXiv  Detail & Related papers  (2026-07-14T22:09:48Z)
• FlowNar: Scalable Streaming Narration for Long-Form Videos [24.674831574110645]
  FlowNar is a novel framework for scalable streaming video narration.<n>The core of FlowNar is a dynamic context management strategy for historical visual context removal.<n> Experiments on the Ego4D, EgoExo4D, and EpicKitchens100 datasets demonstrate that FlowNar substantially improves narration quality over strong baselines.
  arXiv  Detail & Related papers  (2026-05-30T08:51:28Z)
• Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding [55.7992006853979]
  SAVEMem is a framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.<n>We present SAVEMem, a training-free dual-stage framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.
  arXiv  Detail & Related papers  (2026-05-08T15:40:40Z)
• WAT: Online Video Understanding Needs Watching Before Thinking [25.136741695647213]
  WAT (Watching Before Thinking) is a two-stage framework for online video reasoning.<n>It separates processing into a query-independent watching stage and a query-triggered thinking stage.<n>It achieves state-of-the-art performance on online video benchmarks, including 77.7% accuracy on StreamingBench and 55.2% on OVO-Bench.
  arXiv  Detail & Related papers  (2026-03-12T13:42:32Z)
• Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory [50.30283773196725]
  Existing approaches rely on key-value caching to accumulate frame-level details over time, but use a limited number of tokens per frame.<n>We propose scaling the token budget to enable more granular-temporal understanding and reasoning.
  arXiv  Detail & Related papers  (2026-02-20T18:59:50Z)
• StreamForest: Efficient Online Video Understanding with Persistent Event Memory [37.73273040737155]
  StreamForest is designed for streaming video understanding.<n>Fine-grained Spatiotemporal Window captures detailed short-term visual cues to improve current scene perception.<n>OnlineIT significantly boosts MLLM performance in both real-time perception and future prediction.
  arXiv  Detail & Related papers  (2025-09-29T14:53:57Z)
• Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams [78.72965584414368]
  We present Flash-VStream, a video-language model that simulates the memory mechanism of human. Compared to existing models, Flash-VStream achieves significant reductions in latency inference and VRAM consumption. We propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding.
  arXiv  Detail & Related papers  (2024-06-12T11:07:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.