Lune

CVPR Findings2026

Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams

Zhenghui Guo, Yuanbin Man, Junyuan Sheng, Bowen Lin, Ahmed Ahmed, Bo Jiang, Boyuan Zhang, Miao Yin, Sian Jin, Omprakash Gnawali, Chengming Zhang

Abstract

Real-time understanding of long video streams remains challenging for vision-language models (VLMs) due to redundant frame processing and rapid forgetting of past context. Existing streaming systems rely on fixed-interval decoding or cache pruning, which either produce repetitive outputs or discard crucial temporal information. We introduce Event-VStream, an event-aware framework that represents continuous video as a sequence of discrete, semantically coherent events. Our system detects meaningful state transitions by integrating motion, semantic, and predictive cues, and triggers the language model's generation only at those boundaries. Each event embedding is consolidated into a persistent memory bank, enabling long-horizon reasoning while maintaining low latency. Across OVOBench-Realtime, and long-form Ego4D evaluations, Event-VStream achieves competitive performance. It improves over a VideoLLM-Online-8B baseline by +10.4 points on OVOBench-Realtime, achieves performance close to Flash-VStream-7B despite using only a general-purpose LLaMA-3-8B text backbone, and maintains around 70% GPT-5 win rate on 2-hour Ego4D streams.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
  • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites Flamingo: a Visual Language Model for Few-Shot Learning
  • Visual Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  • Visual Instruction Tuning cites Flamingo: a Visual Language Model for Few-Shot Learning
  • BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
  • BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models cites Flamingo: a Visual Language Model for Few-Shot Learning
  • Flamingo: a Visual Language Model for Few-Shot Learning cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on23

  1. Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
  2. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
  3. Flamingo: a Visual Language Model for Few-Shot LearningJean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech et al.NeurIPS 2022 · 6,707 citations
  4. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
  5. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong et al.NeurIPS 2023 · 4,013 citations

Related papers

  1. Flash-Vstream: Efficient Real-Time Understanding for Long Video StreamsHaoji Zhang, Yiqin Wang, Yansong Tang, Yong Liu et al.ICCV 2025 · 15 citations
  2. Vista: Scene-Aware Optimization for Streaming Video Question Answering Under Post-Hoc QueriesHaocheng Lu, Nan Zhang, Wei Tao, Xiaoyang Qu et al.AAAI 2026 · 1 citation
  3. MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video UnderstandingBo He, Hengduo Li, Young Kyun Jang, Menglin Jia et al.CVPR 2024
  4. VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMsNaishan Zheng, Qingpei Guo, Jie Huang, Feng ZhaoCVPR Findings 2026
  5. StreamingVLM: Real-Time Understanding for Infinite Video StreamsRuyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He et al.ICLR 2026 · 95 citations
Dusk over the sea between two cliffs drawn in fine vertical lines