Overview

Visual token pruning studies how to remove or merge image and video patches before or inside vision transformers and vision-language models, reducing computation and memory for tasks such as visual question answering, video understanding, document reading, and robot control. Methods use attention or text-query relevance, feature diversity and spatial coverage, and signals such as entropy, spectral structure, or geometry; learned selectors and adaptive budgets choose different tokens or compression rates for different inputs. Pruning can happen before visual encoding, across language-model layers, or during video processing, and is evaluated on both task benchmarks and practical measures such as prefill latency, FLOPs, and memory. The central tension is that a token that seems redundant early may become important for later reasoning, while selection overhead and hardware execution can prevent fewer tokens from yielding faster end-to-end inference.

Latest papers

CardsList

298 papers23 papers in the last four weeks, down 48% on the four weeks before. 0.2% of all new papers.

  1. SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models

    Sep 1, 2026Shiyu Li, Zi-Yuan Hu, Shijia Huang +3Efficient VLM InferenceMultimodal Large Language Models

  2. From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers

    Sep 1, 2026Siyi Liu, Hanjun Yang, Chenchen Zhang +7Efficient VLM InferenceMultimodal Reranking

  3. PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

    Aug 27, 2026Junjie Liu, Shengyuan Ye, Xu ChenEfficient VLM InferenceVisual Token Pruning

  4. Multi-Image Visual Token Pruning in Large Visual Language Models

    Aug 27, 2026Rongyang Zhang, Chengqiang Lu, Cong Li +9Efficient VLM InferenceLarge Vision-Language Models

  5. Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More

    Aug 26, 2026Chaofang Ma, Lin Jiang, Carol Jingyi Li +4Efficient VLM InferenceVisual Token Pruning

  6. HAP: Head-Adaptive Visual Token Pruning via Cross-Modal Alignment

    Aug 24, 2026Yuanhao Sun, Huawei Ji, Yuan Jin +3Visual Token PruningEfficient VLM Inference

  7. E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models

    Aug 24, 2026Taoyu Qian, Qi Wang, Daqian Shi +3Visual Token PruningEfficient VLM Inference

  8. FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decoding

    Aug 24, 2026Hengjie Zhu, Dayan Wu, Zihao Zhang +6Efficient Multimodal InferenceVLM Inference

  9. RS3^3-Prune: Read-Sparse, Store-Sparse Token Pruning for Video Object Segmentation

    Aug 23, 2026Avilasha Mandal, Sarvesh ShashikumarVideo Object SegmentationVideo Token Compression

  10. Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

    Aug 21, 2026Zhuoyuan Li, Rui Zhao, Jin Wang +5Vision-Language-Action ModelsVisual Token Pruning

  11. Clustering and Token Denoising for Faster and More Robust VLMs

    Aug 19, 2026Baptiste Rossigneux, Inna Kucher, Vincent Lorrain +1Visual Token PruningVisual Token Compression

  12. Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

    Aug 17, 2026Jia Guo, Xiaohan Zhao, Changwang Liu +4Visual Token CompressionVisual Token Pruning

  13. SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Models

    Aug 15, 2026Kexin Ma, Jing Xiao, Bowen Xing +2Remote Sensing VLMsVisual Token Pruning

  14. CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport

    Aug 13, 2026Peng Ling, Yingda Yin, Lingting Zhu +53D Spatial ReasoningVisual Token Pruning

  15. Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers

    Aug 11, 2026Hongsen Cao, Mona Jaber, Shanxin Yuan +1Token PruningEfficient ViTs

  16. When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

    Aug 11, 2026Congyang Ou, Ruike Song, Yang Zhou +3Efficient VLM InferenceLarge Vision-Language Models

  17. Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction

    Aug 9, 2026Aya Manel Zitouni, Aicha Zenakhri, Karim Haroun +1Efficient ViTsFacial Expression Recognition

  18. Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs

    Aug 9, 2026Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim +1Efficient Multimodal InferenceAudio Token Compression

  19. An AI4AI Framework for Visual Token Pruning

    Aug 7, 2026Zhen Liu, Wenli Huang, Wei Song +3Automated Algorithm DiscoveryEfficient VLM Inference

  20. RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs

    Aug 7, 2026Qiyanhui Lu, Han Wu, Rongjian Xu +6Efficient VLM InferenceLarge Vision-Language Models

  21. HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

    Aug 5, 2026Jiuhe Qu, Yingping Liang, Ying Fu3D Spatial ReasoningVisual Token Pruning

  22. DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models

    Aug 5, 2026Chen Zhong, Xiao An, Zijie Wang +3Efficient VLM InferenceVisual Token Pruning

  23. RUTA: Principled Visual Token Allocation via Rate-Utility Optimization

    Aug 4, 2026Jian Zou, Xiaoyu Xu, Zhihua Wang +3Efficient VLM InferenceVisual Token Pruning

  24. Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection

    Aug 4, 2026Yanning Hou, Jingyuan Zhang, Xiaoyun Wang +3Medical Image Anomaly DetectionIndustrial Anomaly Detection

  25. Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Pruning

    Aug 4, 2026Yuyao Sun, Tao Deng, Shuang Li +3Visual AttentionEfficient VLM Inference

  26. Content-Aware Adaptive Token Pruning for Video-Language Models

    Aug 4, 2026Paribesh Regmi, Qingshuang Chen, Chi Zhang +3Efficient VLM InferenceVideo-Language Models