# StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

arXiv: https://arxiv.org/abs/2511.07278 · HTML: https://mlsanity.com/paper/2511.07278/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving.
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction](https://mlsanity.com/paper/2501.03218/) (2025)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning](https://mlsanity.com/paper/2410.19258/) (2024)
- [MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning](https://mlsanity.com/paper/2409.20566/) (2024)
- [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](https://mlsanity.com/paper/2503.03663/) (2025)
- [VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation](https://mlsanity.com/paper/2408.16730/) (2024)
- [StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition](https://mlsanity.com/paper/2503.06220/) (2025)
- [MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders](https://mlsanity.com/paper/2501.01709/) (2025)
- [SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs](https://mlsanity.com/paper/2506.05344/) (2025)

## Built on by (most cited first, 26 of 26)

- [HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2601.14724/) (2026)
- [Thinking in Streaming Video](https://mlsanity.com/paper/2603.12938/) (2026)
- [EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use](https://mlsanity.com/paper/2602.15329/) (2026)
- [Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2603.11896/) (2026)
- [ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding](https://mlsanity.com/paper/2601.10323/) (2026)
- [CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management](https://mlsanity.com/paper/2603.19571/) (2026)
- [CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference](https://mlsanity.com/paper/2604.06036/) (2026)
- [ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding](https://mlsanity.com/paper/2607.28312/) (2026)
- [OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs](https://mlsanity.com/paper/2606.07577/) (2026)
- [Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2606.25658/) (2026)
- [FOLIO: Focused Semantic Memory for Streaming Video Understanding](https://mlsanity.com/paper/2607.13298/) (2026)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding](https://mlsanity.com/paper/2603.21493/) (2026)
- [ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding](https://mlsanity.com/paper/2609.02780/) (2026)
- [Linear Scaling Video VLMs for Long Video Understanding](https://mlsanity.com/paper/2605.31598/) (2026)
- [StreamFlow: Dynamic Memory Flows for Streaming Video Understanding](https://mlsanity.com/paper/2608.10949/) (2026)
- [StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models](https://mlsanity.com/paper/2608.27881/) (2026)
- [Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding](https://mlsanity.com/paper/2609.04131/) (2026)
- [MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding](https://mlsanity.com/paper/2609.38900/) (2026)
- [Learning to See What You Need: Gaze Attention for Multimodal Large Language Models](https://mlsanity.com/paper/2605.13080/) (2026)
- [ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning](https://mlsanity.com/paper/2607.19547/) (2026)
- [Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs](https://mlsanity.com/paper/2609.10355/) (2026)
- [DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video](https://mlsanity.com/paper/2609.27470/) (2026)
- [LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception](https://mlsanity.com/paper/2609.39938/) (2026)
- [ReMem: Streaming Video Understanding With Long Context Retention](https://mlsanity.com/paper/2610.05940/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose StreamKV, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on public StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency. The code has been released at https://github.com/sou1p0wer/StreamKV.