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. P4Q: Co-designing Token Pruning and Quantization for Vision-Language Model Acceleration

    Sep 28, 2026Haizhao Jing, Zhenhao Shang, Haokui Zhang +2VLM QuantizationEfficient VLM Inference

  2. When Text Matters: Design Principles for Visual Token Pruning in Vision-Language Model

    Sep 28, 2026Minchan Kang, Kyeonghye Park, Seoyoung Cho +2Efficient VLM InferenceVisual Token Pruning

  3. ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs

    Sep 28, 2026Xu Li, Yuxuan Liang, Yi Zheng +6Efficient VLM InferenceLarge Vision-Language Models

  4. MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference

    Sep 28, 2026Tinghao Wang, Yichen Guo, Qizhe Zhang +11Efficient Multimodal InferenceMultimodal Large Language Models

  5. DORA: Dynamic Online Reinforcement Agent for Token Pruning in Vision Transformers

    Sep 28, 2026Kaixuan He, Song Chen, Yi KangVision TransformerEfficient ViTs

  6. SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models

    Sep 28, 2026Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk +12Efficient VLM InferenceOn-Policy Self-Distillation

  7. From Token Importance to Conditional Removability: Rethinking Visual Token Pruning in Multimodal Large Language Models

    Sep 22, 2026Shengli He, Yongchao Liang, Roumeng He +5Visual Token PruningMultimodal Token Compression

  8. Shallow to Deep: Aligning Token Pruning with Stage-wise Roles in LVLMs

    Sep 22, 2026Shuo Zhang, Jintao Tong, Yixiong Zou +2Visual Token PruningEfficient VLM Inference

  9. SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models

    Sep 21, 2026Ali Kerem Bozkurt, Baris Cem Bakay, Ibrahim Kulac +3Efficient Multimodal InferenceMultimodal Large Language Models

  10. VPRune: Efficient Training-free Pre-LLM Visual Token Pruning

    Sep 21, 2026Guangchuan Lv, Dianxing Shi, Dingjie FuEfficient VLM InferenceLarge Vision-Language Models

  11. Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

    Sep 20, 2026Yahong Wang, Zhangkai Ni, Juncheng Wu +3Efficient Multimodal InferenceMultimodal Large Language Models

  12. RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory

    Sep 20, 2026Hongbo Mao, Junjun Jiang, Youyu Chen +3Streaming 3D ReconstructionFeed-Forward 3D Reconstruction

  13. QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning

    Sep 17, 2026Shengli He, Yongchao Liang, Roumeng He +4Multimodal Large Language ModelsVisual Token Pruning

  14. Region-Level Policy Optimization for Fine-grained MLLM Perception

    Sep 17, 2026Yuheng Shi, Xiaohuan Pei, Minjing Dong +1Efficient VLM InferenceLarge Vision-Language Models

  15. Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models

    Sep 14, 2026Md Khalid Syfullah, Alvi Ataur KhalilVisual Question AnsweringPrivacy Protection in VLMs

  16. StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models

    Sep 12, 2026Hansen Zhang, Landi He, Mingde Yao +1Efficient VLM InferenceVisual Token Pruning

  17. Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs

    Sep 9, 2026Haiji Liang, Pengfei Zhou, Zhenglin Wan +3Efficient VLM InferenceLarge Vision-Language Models

  18. TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

    Sep 9, 2026Yuhao Wang, Mu Qiao, Xindong Zhang +3KV-Cache CompressionVisual Token Pruning

  19. CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

    Sep 8, 2026Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu +73D Spatial ReasoningVisual Token Pruning

  20. ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics

    Sep 7, 2026Boliang Liu, Wint Yi Poe, Jingyun Di +2Efficient VLA Model InferenceEfficient VLA Models

  21. Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval

    Sep 7, 2026PS Rishi, Rajeev Ranjan Dwivedi, Vinod K KurmiLate Interaction RetrievalToken Pruning

  22. STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

    Sep 5, 2026Yichen Guo, Tinghao Wang, Qizhe Zhang +15Efficient VLM InferenceVisual Token Pruning

  23. LookThere! Sparse Vision by Reinforced Selection

    Sep 4, 2026Sreehari Rammohan, Yousef Yassin, Anthony Fuller +3Efficient ViTsVisual Token Pruning

  24. TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models

    Sep 3, 2026Mehedi Hasan, Ashfak Yeafi, Md Khairul IslamComputational PathologyPathology Foundation Models

  25. Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization

    Sep 2, 2026Qingchan Zhu, Weihang You, Hanqi Jiang +3Efficient VLM InferenceVisual Token Pruning

  26. S2^2Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models

    Sep 1, 2026Yuanyuan Jia, Shunpu Tang, Qianqian YangEfficient VLM InferenceMultimodal Large Language Models