# PruneVid: Visual Token Pruning for Efficient Video Large Language Models

arXiv: https://arxiv.org/abs/2412.16117 · HTML: https://mlsanity.com/paper/2412.16117/

## Key facts

- Cited by 67 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 19 of its 38 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## 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, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)
- [SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models](https://mlsanity.com/paper/2407.15841/) (2024)
- [FreeVA: Offline MLLM as Training-Free Video Assistant](https://mlsanity.com/paper/2405.07798/) (2024)

## Built on by (most cited first, 30 of 67)

- [StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling](https://mlsanity.com/paper/2507.05240/) (2025)
- [HoliTom: Holistic Token Merging for Fast Video Large Language Models](https://mlsanity.com/paper/2505.21334/) (2025)
- [FastVID: Dynamic Density Pruning for Fast Video Large Language Models](https://mlsanity.com/paper/2503.11187/) (2025)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [StreamingTOM: Streaming Token Compression for Efficient Video Understanding](https://mlsanity.com/paper/2510.18269/) (2025)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding](https://mlsanity.com/paper/2603.02096/) (2026)
- [LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs](https://mlsanity.com/paper/2506.21862/) (2025)
- [A Survey of Token Compression for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2507.20198/) (2025)
- [LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs](https://mlsanity.com/paper/2603.19217/) (2026)
- [OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models](https://mlsanity.com/paper/2511.14582/) (2025)
- [FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging](https://mlsanity.com/paper/2602.08024/) (2026)
- [Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior](https://mlsanity.com/paper/2512.06866/) (2025)
- [Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models](https://mlsanity.com/paper/2503.16257/) (2025)
- [MVP: Multiple View Prediction Improves GUI Grounding](https://mlsanity.com/paper/2512.08529/) (2025)
- [Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing](https://mlsanity.com/paper/2603.12254/) (2026)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [UniComp: Rethinking Video Compression Through Informational Uniqueness](https://mlsanity.com/paper/2512.03575/) (2025)
- [FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding](https://mlsanity.com/paper/2511.00141/) (2025)
- [Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2603.02872/) (2026)
- [DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression](https://mlsanity.com/paper/2603.15685/) (2026)
- [Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention](https://mlsanity.com/paper/2603.21957/) (2026)
- [SpecVLM: Fast Speculative Decoding in Vision-Language Models](https://mlsanity.com/paper/2509.11815/) (2025)
- [ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling](https://mlsanity.com/paper/2603.22911/) (2026)
- [Geometry-Guided 3D Visual Token Pruning for Video-Language Models](https://mlsanity.com/paper/2604.18260/) (2026)
- [DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning](https://mlsanity.com/paper/2604.22281/) (2026)
- [EarlyTom: Early Token Compression Completes Fast Video Understanding](https://mlsanity.com/paper/2605.30010/) (2026)
- [AVIS: Adaptive Test-Time Scaling for Vision-Language Models](https://mlsanity.com/paper/2606.11576/) (2026)
- [WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs](https://mlsanity.com/paper/2602.22142/) (2026)
- [Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding](https://mlsanity.com/paper/2603.05663/) (2026)

## Abstract (arXiv)

In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended capabilities in comprehending visual modalities. However, the substantial redundancy in video data presents significant computational challenges for LLMs. To address this issue, we introduce a training-free method that 1) minimizes video redundancy by merging spatial-temporal tokens, and 2) leverages LLMs' reasoning capabilities to selectively prune visual features relevant to question tokens, enhancing model efficiency. We validate our method across multiple video benchmarks, which demonstrate that PruneVid can prune over 80% of tokens while maintaining competitive performance combined with different model networks. This highlights its superior effectiveness and efficiency compared to existing pruning methods. Code: https://github.com/Visual-AI/PruneVid.