# Visual token pruning in multimodal models

Area: [Efficient LLM inference and serving](https://mlsanity.com/inference/index.md). HTML: https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/

## Key facts

- Visual token pruning in multimodal models: 520 papers on arXiv since 2021 (data through 7 Oct 2026).
- 243 of its 520 mapped papers (47%) cite “An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models” (2024, arXiv 2403.06764).
- 182 of its 520 mapped papers (35%) cite “LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models” (2024, arXiv 2403.15388).
- 22 new papers 24 Sep–7 Oct.

## Most cited here

- [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), cited by 243 papers here
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024), cited by 182 papers here
- [DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2503.02175/) (2025), cited by 112 papers here
- [Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More](https://mlsanity.com/paper/2502.11494/) (2025), cited by 95 papers here
- [Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs](https://mlsanity.com/paper/2412.01818/) (2024), cited by 89 papers here
- [Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models](https://mlsanity.com/paper/2409.10197/) (2024), cited by 67 papers here
- [Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs](https://mlsanity.com/paper/2506.10967/) (2025), cited by 62 papers here
- [HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models](https://mlsanity.com/paper/2408.10945/) (2024), cited by 60 papers here
- [ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models](https://mlsanity.com/paper/2412.00447/) (2024), cited by 49 papers here
- [TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model](https://mlsanity.com/paper/2503.18278/) (2025), cited by 42 papers here

## New (24 Sep–7 Oct)

- [Adaptive Visual Token Reduction for Accelerated Image Understanding](https://mlsanity.com/paper/2610.09252/) (2026-10-07)
- [DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models](https://mlsanity.com/paper/2610.08341/) (2026-10-06)
- [VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2610.08133/) (2026-10-06)
- [VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs](https://mlsanity.com/paper/2610.07987/) (2026-10-06)
- [When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA](https://mlsanity.com/paper/2610.05273/) (2026-10-04)
- [MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs](https://mlsanity.com/paper/2610.01434/) (2026-10-01)
- [CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding](https://mlsanity.com/paper/2609.39924/) (2026-09-30)
- [When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic](https://mlsanity.com/paper/2609.39704/) (2026-09-30)
- [Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models](https://mlsanity.com/paper/2609.39134/) (2026-09-30)
- [TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning](https://mlsanity.com/paper/2609.37581/) (2026-09-29)
- [GleanVID: Complementary Token Selection for Efficient Video Large Language Models](https://mlsanity.com/paper/2609.37042/) (2026-09-29)
- [Representation Dynamics Reveal Semantic Saliency and Similarity for Visual Token Pruning in MLLMs](https://mlsanity.com/paper/2609.36916/) (2026-09-29)
- [Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline](https://mlsanity.com/paper/2609.35394/) (2026-09-28)
- [Beyond Selection: Token Parameterization for Extreme Visual Token Compression](https://mlsanity.com/paper/2609.35232/) (2026-09-28)
- [Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models](https://mlsanity.com/paper/2609.35002/) (2026-09-28)
- [SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models](https://mlsanity.com/paper/2609.34977/) (2026-09-28)
- [P4Q: Co-designing Token Pruning and Quantization for Vision-Language Model Acceleration](https://mlsanity.com/paper/2609.34867/) (2026-09-28)
- [When Text Matters: Design Principles for Visual Token Pruning in Vision-Language Model](https://mlsanity.com/paper/2609.34861/) (2026-09-28)
- [ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs](https://mlsanity.com/paper/2609.34558/) (2026-09-28)
- [MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference](https://mlsanity.com/paper/2609.34330/) (2026-09-28)
- [CoViST: Visual Token Compression via Composable States](https://mlsanity.com/paper/2609.33397/) (2026-09-27)
- [Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction](https://mlsanity.com/paper/2609.32353/) (2026-09-26)