# Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction

arXiv: https://arxiv.org/abs/2412.00556 · HTML: https://mlsanity.com/paper/2412.00556/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 49 of its 55 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- 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 49)

- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [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)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)

## Built on by (most cited first, 28 of 28)

- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [A Survey of Token Compression for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2507.20198/) (2025)
- [Efficient Multi-modal Large Language Models via Progressive Consistency Distillation](https://mlsanity.com/paper/2510.00515/) (2025)
- [FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning](https://mlsanity.com/paper/2507.23318/) (2025)
- [Vision Function Layer in Multimodal LLMs](https://mlsanity.com/paper/2509.24791/) (2025)
- [CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms](https://mlsanity.com/paper/2505.17020/) (2025)
- [The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating](https://mlsanity.com/paper/2603.07135/) (2026)
- [Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs](https://mlsanity.com/paper/2512.19918/) (2025)
- [ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance](https://mlsanity.com/paper/2505.18757/) (2025)
- [LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation](https://mlsanity.com/paper/2512.16891/) (2025)
- [Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation](https://mlsanity.com/paper/2607.14557/) (2026)
- [Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models](https://mlsanity.com/paper/2601.12042/) (2026)
- [Stateful Token Reduction for Long-Video Hybrid VLMs](https://mlsanity.com/paper/2603.00198/) (2026)
- [ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling](https://mlsanity.com/paper/2603.22911/) (2026)
- [EarlyTom: Early Token Compression Completes Fast Video Understanding](https://mlsanity.com/paper/2605.30010/) (2026)
- [METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models](https://mlsanity.com/paper/2507.20842/) (2025)
- [Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM](https://mlsanity.com/paper/2505.15816/) (2025)
- [GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models](https://mlsanity.com/paper/2506.13166/) (2025)
- [Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding](https://mlsanity.com/paper/2507.09334/) (2025)
- [MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs](https://mlsanity.com/paper/2604.03072/) (2026)
- [Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance](https://mlsanity.com/paper/2509.15704/) (2025)
- [Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs](https://mlsanity.com/paper/2604.02689/) (2026)
- [VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models](https://mlsanity.com/paper/2604.15188/) (2026)
- [ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs](https://mlsanity.com/paper/2606.00543/) (2026)
- [MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs](https://mlsanity.com/paper/2606.31383/) (2026)
- [PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models](https://mlsanity.com/paper/2607.22726/) (2026)
- [OVIBench: Benchmarking Online Video Question Answering under Interruption](https://mlsanity.com/paper/2608.22279/) (2026)

## Abstract (arXiv)

Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs) process the text tokens. However, the number of vision tokens increases quadratically as the image resolutions, leading to huge computational costs. In this paper, we consider improving MLLM's efficiency from two scenarios, (I) Reducing computational cost without degrading the performance. (II) Improving the performance with given budgets. We start with our main finding that the ranking of each vision token sorted by attention scores is similar in each layer except the first layer. Based on it, we assume that the number of essential top vision tokens does not increase along layers. Accordingly, for Scenario I, we propose a greedy search algorithm (G-Search) to find the least number of vision tokens to keep at each layer from the shallow to the deep. Interestingly, G-Search is able to reach the optimal reduction strategy based on our assumption. For Scenario II, based on the reduction strategy from G-Search, we design a parametric sigmoid function (P-Sigmoid) to guide the reduction at each layer of the MLLM, whose parameters are optimized by Bayesian Optimization. Extensive experiments demonstrate that our approach can significantly accelerate those popular MLLMs, e.g. LLaVA, and InternVL2 models, by more than 2 × without performance drops. Our approach also far outperforms other token reduction methods when budgets are limited, achieving a better trade-off between efficiency and effectiveness.