# StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding

arXiv: https://arxiv.org/abs/2512.12560 · HTML: https://mlsanity.com/paper/2512.12560/

## Key facts

- Cited by 10 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 30 of its 37 references that are in the map.
- First posted on arXiv 14 Dec 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 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [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)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [VideoLLM-online: Online Video Large Language Model for Streaming Video](https://mlsanity.com/paper/2406.11816/) (2024)
- [DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2503.02175/) (2025)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos](https://mlsanity.com/paper/2504.17343/) (2025)
- [Online Video Understanding: OVBench and VideoChat-Online](https://mlsanity.com/paper/2501.00584/) (2024)
- [HoliTom: Holistic Token Merging for Fast Video Large Language Models](https://mlsanity.com/paper/2505.21334/) (2025)
- [VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation](https://mlsanity.com/paper/2408.16730/) (2024)
- [Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning](https://mlsanity.com/paper/2503.00513/) (2025)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance](https://mlsanity.com/paper/2501.02430/) (2025)
- [StreamChat: Chatting with Streaming Video](https://mlsanity.com/paper/2412.08646/) (2024)
- [Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU](https://mlsanity.com/paper/2409.09086/) (2024)
- [Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI](https://mlsanity.com/paper/2507.10510/) (2025)

## Built on by (most cited first, 10 of 10)

- [A Simple Baseline for Streaming Video Understanding](https://mlsanity.com/paper/2604.02317/) (2026)
- [VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration](https://mlsanity.com/paper/2601.22674/) (2026)
- [What Should a Streaming Video Model Remember?](https://mlsanity.com/paper/2606.16353/) (2026)
- [Unlocking Dense Metric Depth Estimation in VLMs](https://mlsanity.com/paper/2605.15876/) (2026)
- [An Efficient Streaming Video Understanding Framework with Agentic Control](https://mlsanity.com/paper/2605.17921/) (2026)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding](https://mlsanity.com/paper/2602.01683/) (2026)
- [Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors](https://mlsanity.com/paper/2606.06891/) (2026)
- [Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence](https://mlsanity.com/paper/2607.20981/) (2026)
- [DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding](https://mlsanity.com/paper/2610.19849/) (2026)

## Abstract (arXiv)

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in high GPU memory usage and computational latency. To address these challenges, we propose token pruning as a means to reduce context length while retaining critical information. Specifically, we introduce a novel redundancy metric, Maximum Similarity to Spatially Adjacent Video Tokens (MSSAVT), which accounts for both token similarity and spatial position. To mitigate the bidirectional dependency between pruning and redundancy, we further design a masked pruning strategy that ensures only mutually unadjacent tokens are pruned. We also integrate an existing temporal redundancy-based pruning method to eliminate temporal redundancy of the video modality. Experimental results on multiple online and offline video understanding benchmarks demonstrate that our method significantly improves the accuracy (i.e., by 4% at most) while incurring a negligible pruning latency (i.e., less than 1ms). Our full implementation will be made publicly available.