Visual Token Pruning

Ask about this topic

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

276 papers43 papers in the last four weeks, up 59% on the four weeks before. 0.2% of all new papers.

  1. LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models

    Oct 27, 2026Rinyoichi Takezoe, Yaqian Li, Weiren Wang +6Visual Token PruningLVLM Pruning

    Li Auto Inc. Beijing, China · Li Auto Inc. Shanghai, China · Li Auto Inc. Hangzhou, China

  2. TP-JSCC: Efficient Token Pruning and Joint Source-Channel Coding for LVLMs-based 3D-VQA in Cloud-Edge Collaboration

    Oct 26, 2026Zhengxin Li, Chongzhen Tian, Hui Yuan +2Visual Token Compression3D VQA

    School of Control Science and Engineering, Shandong University, Jinan 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250061, China · Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Jinan 250100, China +2

  3. VTC-AUDIT: An Interventional Reliability Audit for Visual-Token Compression under Paired Image Shifts

    Oct 25, 2026Isaac, LiVisual Token CompressionVLM Evaluation

    Rucheng · University of Pittsburgh

  4. TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning

    Oct 25, 2026Sooyoung Kwon, Carlee Joe-Wong, Kyunghan LeeEfficient VLA Model InferenceVisual Token Pruning

    Dept. of ECE, Seoul National University. · Dept. of ECE, Carnegie Mellon University.

  5. Rescuing Your Pruning: Rethinking Visual Token Pruning and Post-Training Recovery in MLLMs

    Oct 24, 2026Peiran Yin, Hao Wu, Zihao Yang +3Visual Token PruningEfficient VLM Inference

    EIT-NLP Lab, Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University · Uppsala University

  6. Vision Token Pruning via Query-Vision Interaction Decomposition

    Oct 23, 2026Harshithanjani Athi, Sravan Kumar Ankireddy, Jianzhong Charlie Zhang +1Efficient VLM InferenceVisual Token Pruning

    1The University of Texas at Austin · 2Samsung Research America

  7. GazeLens for Efficient Egocentric Video Question Answering with Simple Gaze-Driven Adaptive Token Reduction

    Oct 20, 2026Trong-Thang Pham, Anh Nguyen, Hien Van Nguyen +1Egocentric Video QAEfficient VLM Inference

  8. Visual Sufficiency Landscapes: Understanding Query-Conditioned Reliability in Visual Token Pruning

    Oct 18, 2026Zhenghan Li, Kexin Sun, Wei Zheng +3Visual Token PruningLVLM Pruning

    School of Software, Northwestern Polytechnical University, Xi’an 710129, China

  9. Are We Evaluating VLM Token Pruning Right? Looking Beyond Accuracy and Token Count

    Oct 17, 2026Geng Li, Guohao Chen, Shilin Shan +1Visual Token PruningVLM Evaluation

    Nanyang Technological University

  10. Hierarchical and Query-Aware Visual Token Pruning for High-Resolution LVLMs

    Oct 16, 2026Luther Wei, Ling Zou, Kang-Yang Huang +2Visual Token PruningEfficient VLM Inference

    Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan · MediaTek Inc., Hsinchu, Taiwan

  11. CatchUp: Depth-Aware Re-Admission of Visual Tokens for Efficient Large Vision-Language Models

    Oct 16, 2026Eunju Park, Uiwon HwangEfficient VLM InferenceLarge Vision-Language Models

    Division of Artificial Intelligence & Software, Ewha Womans University

  12. MedSTP: Preserving Subspace and Transition Evidence for Medical VQA Token Pruning

    Oct 15, 2026Mengchen Fan, Qizhen Lan, Xi Xiao +6Visual Token PruningMedical VQA

    University of Alabama at Birmingham · UTHealth Houston · Northeastern University +1

  13. STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents

    Oct 14, 2026Shuo Wang, Sifan Zhou, Xiaobo Wang +6Visual Token PruningEfficient VLM Inference

    Mininglamp · Southeast University · Shenzhen University of Advanced Technology

  14. Complementary Future Token Pruning for World Action Models

    Oct 14, 2026Baekseung Kim, Junhoo Lee, Sohyeon Hong +5Efficient Inference for World Action ModelsVisual Token Pruning

    Seoul National University · Korea Advanced Institute of Science & Technology · Dnotitia

  15. Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning

    Oct 13, 2026Tianhao Fu, Austin Wang, Charles Chen +5Visual Token CompressionEfficient VLM Inference

    University of Toronto, Toronto, ON, Canada · Vector Institute, Toronto, ON, Canada · McGill University, Montreal, QC, Canada +2

  16. Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs

    Oct 13, 2026Peiran Yin, Hao Wu, Zihao Yang +6Visual Token PruningEfficient VLM Inference

    EIT-NLP Lab, Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University · Uppsala University +1

  17. Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression

    Oct 13, 2026Vatsal, Soumil Malhotra, Priyanshu Chahal +1Vision TransformerEfficient ViTs

    Department of Mathematics, Indian Institute of Technology Roorkee

  18. How Much Can We Prune? Exploring the Performance Limits of Visual Token Pruning

    Oct 13, 2026Janghoon Cho, Shubhankar Borse, Reza Pourreza +4Visual Token PruningLVLM Pruning

    Qualcomm AI Research∗

  19. TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models

    Oct 13, 2026Kai Liu, Anqi Li, Junxian Li +4Efficient VLM InferenceVisual Token Pruning

    Shanghai Jiao Tong University · Huawei Technologies Ltd

  20. FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models

    Oct 12, 2026Zihan Meng, Weidong Chen, Dexiang Hong +2Efficient VLM InferenceVisual Token Pruning

    University of Science and Technology of China · Harbin Institute of Technology

  21. When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction

    Oct 12, 2026Yihang Huang, Peisong Wen, Chenhao Zhou +2Efficient VLM InferenceVisual Token Pruning

    State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences School of Computer Science and Technology, University of Chinese Academy of Sciences Beijing, China · School of Computer Science and Technology, University of Chinese Academy of Sciences Beijing, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences Beijing Academy of Artificial Intelligence Beijing, China

  22. SheafPrune: Sheaf-Guided Graph Propagation for Visual Token Pruning

    Oct 9, 2026Xiaoyang Ma, Chi Wang, Hong SunVisual Token PruningEfficient VLM Inference

    PHOENIX Lab Hangzhou Dianzi University Hangzhou, 310018, China

  23. Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning

    Oct 8, 2026Yicheng Xue, Han Wu, Jufeng Yang +4VLM ReasoningEfficient Multimodal Inference

    City University of Hong Kong · Zhejiang University · Peking University +2

  24. Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs

    Oct 7, 2026Shuailong Wang, Xinyu Lyu, Shengming Yuan +3Visual Token PruningVLM Robustness

    University of Electronic Science and Technology of China, Chengdu, China · Southwestern University of Finance and Economics, Chengdu, China · Tongji University, Shanghai, China +1

  25. Adaptive Visual Token Reduction for Accelerated Image Understanding

    Oct 7, 2026Seyoung Jeong, Jong Pil Yun, Sang Jun LeeEfficient VLM InferenceVisual Token Pruning

    Jeonbuk National University, Jeonju, Republic of Korea · Korea Institute of Industrial Technology (KITECH), Incheon, Republic of Korea · Chung-Ang University, Seoul, Republic of Korea

  26. DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models

    Oct 6, 2026Shuo Yang, Changbai Li, Linlin Yang +6Multimodal Large Language ModelsToken Pruning

    Beihang University · Communication University of China · National University of Singapore

  27. VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models

    Oct 6, 2026Owen Du, Yang Yue, Jie Zhang +3Efficient VLA ModelsVLMs for Robotics

    ETH Zurich · Tsinghua University

  28. Later Is Better: Token Reduction for ViTs Under Distribution Shift

    Oct 6, 2026Hyeongheon Cha, Hyungjun Yoon, Sung-Ju LeeDistribution Shift RobustnessToken Pruning

    KAIST

  29. Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMs

    Oct 6, 2026Donghyun Han, Jangho Park, Yuseok BaeEfficient VLM InferenceVisual Token Pruning

    ETRI, South Korea · Kyung Hee University, South Korea

  30. When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA

    Oct 4, 2026Tianjun Shi, Haotian Xiong, Ziyu Gong +2Efficient VLA Model InferenceVision-Language-Action Models

    University of Macau