# What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph

arXiv: https://arxiv.org/abs/2501.02268 · HTML: https://mlsanity.com/paper/2501.02268/

## Key facts

- Cited by 36 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 23 of its 43 references that are in the map.
- First posted on arXiv 4 Jan 2025.

## 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, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [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)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output](https://mlsanity.com/paper/2407.03320/) (2024)
- [Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference](https://mlsanity.com/paper/2405.05803/) (2024)
- [DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models](https://mlsanity.com/paper/2405.20985/) (2024)
- [PuMer: Pruning and Merging Tokens for Efficient Vision Language Models](https://mlsanity.com/paper/2305.17530/) (2023)

## Built on by (most cited first, 30 of 36)

- [A Survey of Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08748/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (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)
- [TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models](https://mlsanity.com/paper/2503.10501/) (2025)
- [Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods](https://mlsanity.com/paper/2510.07143/) (2025)
- [TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation](https://mlsanity.com/paper/2504.17365/) (2025)
- [Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models](https://mlsanity.com/paper/2511.02650/) (2025)
- [Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects](https://mlsanity.com/paper/2604.05546/) (2026)
- [ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance](https://mlsanity.com/paper/2505.18757/) (2025)
- [VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference](https://mlsanity.com/paper/2508.17857/) (2025)
- [On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression](https://mlsanity.com/paper/2601.21531/) (2026)
- [D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs](https://mlsanity.com/paper/2511.12280/) (2025)
- [EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling](https://mlsanity.com/paper/2604.17087/) (2026)
- [Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation](https://mlsanity.com/paper/2607.14557/) (2026)
- [Attention Debiasing for Token Pruning in Vision Language Models](https://mlsanity.com/paper/2508.17807/) (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)
- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2606.25658/) (2026)
- [Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding](https://mlsanity.com/paper/2507.09334/) (2025)
- [CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.09266/) (2025)
- [AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance](https://mlsanity.com/paper/2508.06084/) (2025)
- [Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning](https://mlsanity.com/paper/2511.19518/) (2025)
- [When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs](https://mlsanity.com/paper/2604.12035/) (2026)
- [AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees](https://mlsanity.com/paper/2605.19260/) (2026)
- [S2Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models](https://mlsanity.com/paper/2609.01224/) (2026)
- [Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs](https://mlsanity.com/paper/2604.02689/) (2026)
- [DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation](https://mlsanity.com/paper/2606.16633/) (2026)
- [GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models](https://mlsanity.com/paper/2607.09080/) (2026)
- [Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference](https://mlsanity.com/paper/2607.15563/) (2026)

## Abstract (arXiv)

Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual redundancy. In this paper, we investigate what kind of visual tokens are needed for MLLMs, and reveal that both foreground and background tokens are critical for MLLMs given the varying difficulties of examples. Based on this observation, we propose a graph-based method towards training-free visual token pruning, termed G-Prune.In particular, G-Prune regards visual tokens as nodes, and construct their connections based on their semantic similarities. Afterwards, the information flow is propagated via weighted links, and the most important tokens after iterations are kept for MLLMs, which can be front or background.To validate G-Prune, we apply it to a recent MLLM called LLaVA-NeXT, and conduct extensive experiments on a set of benchmarks.The experiment results show that G-Prune can greatly reduce computation overhead while retaining high performance on both coarse- and fine-grained tasks. For instance, G-Prune can reduce 63.57% FLOPs of LLaVA-NeXT on VQA2.0 and TextVQA with only 0.95% and 2.34% accuracy drops, respectively.