# Similarity-Aware Token Pruning: Your VLM but Faster

arXiv: https://arxiv.org/abs/2503.11549 · HTML: https://mlsanity.com/paper/2503.11549/

## Key facts

- Cited by 35 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 40 of its 43 references that are in the map.
- First posted on arXiv 14 Mar 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 / [Token pruning and merging for ViTs](https://mlsanity.com/inference/token-pruning-and-merging-for-vits/)

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [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)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [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)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)

## Built on by (most cited first, 30 of 35)

- [Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs](https://mlsanity.com/paper/2506.10967/) (2025)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [N"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning](https://mlsanity.com/paper/2602.02951/) (2026)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models](https://mlsanity.com/paper/2605.28051/) (2026)
- [VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm](https://mlsanity.com/paper/2512.02700/) (2025)
- [D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs](https://mlsanity.com/paper/2511.12280/) (2025)
- [AVIS: Adaptive Test-Time Scaling for Vision-Language Models](https://mlsanity.com/paper/2606.11576/) (2026)
- [Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs](https://mlsanity.com/paper/2603.16932/) (2026)
- [HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models](https://mlsanity.com/paper/2604.07812/) (2026)
- [RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction](https://mlsanity.com/paper/2605.04075/) (2026)
- [Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction](https://mlsanity.com/paper/2606.24156/) (2026)
- [Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models](https://mlsanity.com/paper/2509.19191/) (2025)
- [Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models](https://mlsanity.com/paper/2512.01949/) (2025)
- [MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs](https://mlsanity.com/paper/2604.03072/) (2026)
- [DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs](https://mlsanity.com/paper/2605.19322/) (2026)
- [Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization](https://mlsanity.com/paper/2609.03158/) (2026)
- [Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models](https://mlsanity.com/paper/2509.25584/) (2025)
- [Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models](https://mlsanity.com/paper/2511.11910/) (2025)
- [Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2606.24165/) (2026)
- [DiffPrune: differentiable information throttling for token pruning in vision-language models](https://mlsanity.com/paper/2608.01985/) (2026)
- [QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning](https://mlsanity.com/paper/2609.19990/) (2026)
- [Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference](https://mlsanity.com/paper/2511.18875/) (2025)
- [Taking Shortcuts for Categorical VQA Using Super Neurons](https://mlsanity.com/paper/2603.10781/) (2026)
- [VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading](https://mlsanity.com/paper/2605.05899/) (2026)
- [RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT](https://mlsanity.com/paper/2606.08156/) (2026)
- [DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation](https://mlsanity.com/paper/2606.16633/) (2026)
- [Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models](https://mlsanity.com/paper/2607.13500/) (2026)
- [From Token Importance to Conditional Removability: Rethinking Visual Token Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2609.26484/) (2026)
- [SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models](https://mlsanity.com/paper/2609.34044/) (2026)

## Abstract (arXiv)

The computational demands of Vision Transformers (ViTs) and Vision-Language Models (VLMs) remain a significant challenge due to the quadratic complexity of self-attention. While token pruning offers a promising solution, existing methods often introduce training overhead or fail to adapt dynamically across layers. We present SAINT, a training-free token pruning framework that leverages token similarity and a graph-based formulation to dynamically optimize pruning rates and redundancy thresholds. Through systematic analysis, we identify a universal three-stage token evolution process (aligner-explorer-aggregator) in transformers, enabling aggressive pruning in early stages without sacrificing critical information. For ViTs, SAINT doubles the throughput of ViT-H/14 at 224px with only 0.6% accuracy loss on ImageNet-1K, surpassing the closest competitor by 0.8%. For VLMs, we apply SAINT in three modes: ViT-only, LLM-only, and hybrid. SAINT reduces LLaVA-13B's tokens by 75%, achieving latency comparable to LLaVA-7B with less than 1% performance loss across benchmarks. Our work establishes a unified, practical framework for efficient inference in ViTs and VLMs.