StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs

• URL: http://arxiv.org/abs/2608.13416v2
• Date: Sun, 16 Aug 2026 09:41:57 GMT
• Title: StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
• Abstract summary: StreamTTT writes long-range history into online-updated fast weights outside the attention context.<n>We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus.<n>It outperforms the same-scale SimpleStream-4B by 1.4 points in real-time perception and 3.7 points in backward tracing.
• Score: 53.38747124102543
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, under each model's reported input protocol, StreamTTT-4B outperforms the same-scale SimpleStream-4B by 1.4 points in real-time perception and 3.7 points in backward tracing. It also remains competitive with the larger SimpleStream-8B on StreamingBench's Real-Time Visual Understanding (RTVU) subset. Our code will be released.

Related papers

• StreamFlow: Dynamic Memory Flows for Streaming Video Understanding [65.10324190760602]
  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.
  arXiv  Detail & Related papers  (2026-08-11T14:19:03Z)
• 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)
• Don't Pause! Every prediction matters in a streaming video [55.509551643600794]
  We introduce SPOT-Bench, featuring multi-turn proactive queries that evaluate general streaming perception and assistive capabilities.<n> SPOT-Bench comes with Timeliness-F1, a metric that measures streaming predictions by their temporal precision and balanced coverage across the entire video.<n>Our benchmark reveals: (i) offline models detect events reliably but spam predictions unprompted; (ii) post-training for silence reduces spamming but induces unresponsiveness; (iii) half of the streaming video expects no response, which we term dead-time - compute spent here does not affect response latency.
  arXiv  Detail & Related papers  (2026-04-27T11:07:03Z)
• A Simple Baseline for Streaming Video Understanding [44.77185258429313]
  We formalize a sliding-window baseline that feeds only the most recent N frames to an off-the-shelf VLM.<n>We evaluate it against 13 major offline and online video LLM baselines on OVO-Bench and StreamingBench.
  arXiv  Detail & Related papers  (2026-04-02T17:58:04Z)
• Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously [69.0264594684213]
  Video Streaming Thinking (VST) is a novel paradigm for streaming video understanding.<n>It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming.<n>VST improves timely comprehension and coherent cognition while preserving real-time responsiveness.
  arXiv  Detail & Related papers  (2026-03-12T17:59:51Z)
• Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams [11.495597616926274]
  Event-VStream represents continuous video as a sequence of discrete, semantically coherent events.<n>System detects meaningful state transitions by integrating motion, semantic, and predictive cues.<n>System maintains around 70% GPT-5 win rate on 2-hour Ego4D streams.
  arXiv  Detail & Related papers  (2026-01-22T05:05:53Z)
• StreamingVLM: Real-Time Understanding for Infinite Video Streams [23.94087606884915]
  StreamingVLM is a model designed for real-time, stable understanding of infinite visual input.<n>Our approach is a unified framework that aligns training with streaming inference.<n>On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100.
  arXiv  Detail & Related papers  (2025-10-10T17:59:58Z)
• 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)

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.