# Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?

arXiv: https://arxiv.org/abs/2502.11501 · HTML: https://mlsanity.com/paper/2502.11501/

## Key facts

- Cited by 76 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 18 of its 33 references that are in the map.
- First posted on arXiv 17 Feb 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, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark](https://mlsanity.com/paper/2407.13766/) (2024)

## Built on by (most cited first, 30 of 76)

- [Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs](https://mlsanity.com/paper/2506.10967/) (2025)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention](https://mlsanity.com/paper/2510.02912/) (2025)
- [Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models](https://mlsanity.com/paper/2505.14454/) (2025)
- [Shifting AI Efficiency From Model-Centric to Data-Centric Compression](https://mlsanity.com/paper/2505.19147/) (2025)
- [Variation-aware Vision Token Dropping for Faster Large Vision-Language Models](https://mlsanity.com/paper/2509.01552/) (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)
- [AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs](https://mlsanity.com/paper/2510.07293/) (2025)
- [DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning](https://mlsanity.com/paper/2509.23883/) (2025)
- [CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning](https://mlsanity.com/paper/2508.07871/) (2025)
- [Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods](https://mlsanity.com/paper/2510.07143/) (2025)
- [Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving](https://mlsanity.com/paper/2508.13305/) (2025)
- [Towards General Continuous Memory for Vision-Language Models](https://mlsanity.com/paper/2505.17670/) (2025)
- [SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference](https://mlsanity.com/paper/2510.17777/) (2025)
- [N"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning](https://mlsanity.com/paper/2602.02951/) (2026)
- [Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models](https://mlsanity.com/paper/2511.02650/) (2025)
- [IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning](https://mlsanity.com/paper/2602.03060/) (2026)
- [VideoNSA: Native Sparse Attention Scales Video Understanding](https://mlsanity.com/paper/2510.02295/) (2025)
- [The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating](https://mlsanity.com/paper/2603.07135/) (2026)
- [Towards Long-horizon Agentic Multimodal Search](https://mlsanity.com/paper/2604.12890/) (2026)
- [ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention](https://mlsanity.com/paper/2602.07574/) (2026)
- [Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework](https://mlsanity.com/paper/2602.19549/) (2026)
- [Innovator-VL: A Multimodal Large Language Model for Scientific Discovery](https://mlsanity.com/paper/2601.19325/) (2026)
- [D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning](https://mlsanity.com/paper/2512.19443/) (2025)
- [What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models](https://mlsanity.com/paper/2603.00510/) (2026)
- [IPCV: Information-Preserving Compression for MLLM Visual Encoders](https://mlsanity.com/paper/2512.18747/) (2025)
- [EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling](https://mlsanity.com/paper/2604.17087/) (2026)
- [Large Vision-Language Models Get Lost in Attention](https://mlsanity.com/paper/2605.05668/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with token pruning, which identifies the redundant tokens in MLLMs and then prunes them to reduce the computation and KV storage costs, leading to significant acceleration without training. While these methods claim efficiency gains, critical questions about their fundamental design and evaluation remain unanswered: Why do many existing approaches underperform even compared to naive random token selection? Are attention-based scoring sufficient for reliably identifying redundant tokens? Is language information really helpful during token pruning? What makes a good trade-off between token importance and duplication? Are current evaluation protocols comprehensive and unbiased? The ignorance of previous research on these problems hinders the long-term development of token pruning. In this paper, we answer these questions one by one, providing insights into the design of future token pruning methods.