Visual Token Pruning

Ask about this topic

Momentum

24 papers in the last four weeks, up 118% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 130

All topics
CardsList

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

    Oct 6, 2026Shuo Yang, Changbai Li, Linlin Yang +6Visual Token PruningMultimodal Large Language Models

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

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

    Oct 4, 2026Tianjun Shi, Haotian Xiong, Ziyu Gong +2Visual Token PruningDiffusion-Based Vision-Language-Actions

    University of Macau

  3. MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs

    Oct 1, 2026Xudong Wang, Hao Wu, Haozhe Hu +5Visual Token PruningLarge Language Model Compression

    EIT-NLP Lab, Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University · The Hong Kong Polytechnic University +1

  4. When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic

    Sep 30, 2026Muhammad Zawish, Steven DavyVisual Token PruningMask2Former

    Technological University Dublin, Ireland

  5. Audio Token Attention Is Predictable Before the Language Model Runs

    Sep 30, 2026Kyoungjun Park, Yunzhe Li, Lili QiuLarge Audio Language ModelsAudio Understanding

    The University of Texas at Austin

  6. TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning

    Sep 29, 2026Jing Wang, Zhiping Wu, Dongdong Ren +3Visual Token PruningRecent Vision-Language Models

    School of Intelligence Science and Technology, Nanjing University · School of Electronic Science and Engineering, Nanjing University · Geely Automobile Research Institute (Ningbo) Co., Ltd., 315000 +1

  7. Hierarchical Compression of Vision-Language Model Benchmarks

    Sep 29, 2026Hyunjong Ok, Seunggu Kang, Jaeho LeeVisual Token PruningMultimodal Evaluation

    Pohang University of Science and Technology · Upstage AI

  8. Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference

    Sep 29, 2026Jiayu Chen, Shuyong Gao, Jingkai Jia +6Visual Token PruningDiffusion-Based Vision-Language-Actions

    Fudan University · The Hong Kong Polytechnic University

  9. SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models

    Sep 28, 2026Tianxiang Chen, Zhentao Tan, Zi Ye +9Visual Token PruningMultimodal Large Language Models

    End-User Intelligent Computing BU, Alibaba Cloud · Alibaba Group · Department of Computer Science, Maynooth University +2

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

    Sep 28, 2026Haizhao Jing, Zhenhao Shang, Haokui Zhang +2Visual Token PruningLarge Language Model Quantization

    Northwest Polytechnical University · Intellifusion

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

    Sep 28, 2026Minchan Kang, Kyeonghye Park, Seoyoung Cho +2Visual Token PruningRecent Vision-Language Models

    Korea Advanced Institute of Science and Technology (KAIST) · Hanbat National University

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

    Sep 28, 2026Xu Li, Yuxuan Liang, Yi Zheng +6Visual Token PruningSaliency

    College of Computer Science and Artificial Intelligence Fudan University, Shanghai, China

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

    Sep 28, 2026Kaixuan He, Song Chen, Yi KangVisual Token PruningVision Transformer

    University of Science and Technology of China, Hefei, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China

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

    Sep 28, 2026Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk +12Visual Token PruningRecent Vision-Language Models

    University of Toronto · Vector Institute · Samsung AI Center Toronto +7

  15. EAT: Expert Account Tracker for Efficient MoE Inference

    Sep 27, 2026Yuexian Li, Yifei Yang, Zouying Cao +1Mixture-Of-ExpertsExperts

    Paris Elite Institute of Technology, Shanghai Jiao Tong University · AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University +1

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

    Sep 21, 2026Ali Kerem Bozkurt, Baris Cem Bakay, Ibrahim Kulac +3Whole-Slide ImagesPathology Foundation Models

    Kocı University, Department of Computer Engineering · Kocı University, Department of Pathology · Hacettepe University, Department of Artificial Intelligence and Data Engineering

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

    Sep 21, 2026Guangchuan Lv, Dianxing Shi, Dingjie FuVisual Token PruningRecent Vision-Language Models

    Northeastern University · Beihang University · Huazhong University of Science and Technology

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

    Sep 20, 2026Yahong Wang, Zhangkai Ni, Juncheng Wu +3Visual Token PruningMultimodal Large Language Models

    Tongji University · University of California, Santa Cruz · East China Normal University +1

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

    Sep 17, 2026Shengli He, Yongchao Liang, Roumeng He +4Visual Token PruningMultimodal Large Language Models

    Guizhou University · Guizhou University, Guiyang, China · Shanghai Ocean University

  20. AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting

    Sep 15, 2026Zhixiang Wu, Yining Liu, Bo Zhao +4Spatio-Temporal ForecastingMulti-Stream Temporal Fusion

    Institute of Computing Technology, Chinese Academy of Sciences, China · Emory University, USA · University of California, Berkeley, USA +3

  21. 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 Token PruningPrivacy

    Transformative Innovation for Trustworthy AI and Network Security (TITANS) Lab, Computer Science, Southern Illinois University Carbondale, USA

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

    Sep 9, 2026Haiji Liang, Pengfei Zhou, Zhenglin Wan +3Visual Token PruningMultimodal Large Language Models

    National University of Singapore · InfRec, Cardinal AI Lab · The Hong Kong University of Science and Technology

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

    Sep 9, 2026Yuhao Wang, Mu Qiao, Xindong Zhang +3Visual Token PruningTraces

    Dalian University of Technology · OPPO Research Institute · The Hong Kong Polytechnic University

  24. Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

    Sep 9, 2026Yaning Jia, Chunhui Zhang, Wenxuan Xu +3Supervised FinetuningMathematical Reasoning Benchmarks

    Dartmouth College · Carnegie Mellon University

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

    Sep 8, 2026Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu +7Visual Token PruningVoxel

    Carnegie Mellon University · Meta Reality Labs

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

    Sep 3, 2026Mehedi Hasan, Ashfak Yeafi, Md Khairul IslamPathology Foundation ModelsWireless Foundation Models

    Department of Computer Science and Engineering, Brac University, Dhaka, Bangladesh · EEE, Khulna University of Engineering & Technology, Khulna, Bangladesh · Mathematics and Computer Science, Hobart and William Smith Colleges, Geneva, NY, USA

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

    Sep 2, 2026Qingchan Zhu, Weihang You, Hanqi Jiang +3Visual Token PruningPrompt Optimization

    School of Computing, University of Georgia · College of Engineering, Northeastern University

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

    Sep 1, 2026Yuanyuan Jia, Shunpu Tang, Qianqian YangVisual Token PruningMultimodal Large Language Models

    College of Information Science and Electronic Engineering, Zhejiang University Hangzhou, China

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

    Sep 1, 2026Shiyu Li, Zi-Yuan Hu, Shijia Huang +3Visual Token PruningLong Visual-Token Sequences

    1The Chinese University of Hong Kong · 2Weitu AI · 3Peking University

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

    Sep 1, 2026Siyi Liu, Hanjun Yang, Chenchen Zhang +7Visual Token PruningLarge Language Model Reranking

    1The Hong Kong University of Science and Technology (Guangzhou) · 2Tencent Yuanbao · 3ARC Lab, Tencent

  31. Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs

    Aug 31, 2026Shunjie Wen, Jaeyeon Lee, Dong-Wan ChoiVisual Token PruningCosine Similarity

    Inha University

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

    Aug 27, 2026Junjie Liu, Shengyuan Ye, Xu ChenVisual Token Pruning

    Sun Yat-sen University · Power Dispatch Control Center, Guangdong Power Grid Co., Ltd. Guangzhou, China · Shenzhen Loop Area Institute, Shenzhen, China

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

    Aug 27, 2026Rongyang Zhang, Chengqiang Lu, Cong Li +9Visual Token Pruning

    State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Xiaohongshu Inc.

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

    Aug 13, 2026Peng Ling, Yingda Yin, Lingting Zhu +5Visual Token Pruning3D Spatial Reasoning

    Shenzhen International Graduate School, Tsinghua University · LIGHTSPEED

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

    Aug 11, 2026Hongsen Cao, Mona Jaber, Shanxin Yuan +1Visual Token PruningSelf-Supervised Vision Transformers

    School of Electronic Engineering and Computer Science Queen Mary University of London London, United Kingdom

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

    Aug 11, 2026Congyang Ou, Ruike Song, Yang Zhou +3Visual Token PruningCross-Modal

    Northwestern Polytechnical University · Chongqing University · MiLM Plus, Xiaomi Inc.

  37. An AI4AI Framework for Visual Token Pruning

    Aug 7, 2026Zhen Liu, Wenli Huang, Wei Song +3Visual Token PruningMultimodal Benchmarks

    Xi’an Jiaotong University · Ningbo University of Technology · 3North China University of Technology +3

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

    Aug 7, 2026Qiyanhui Lu, Han Wu, Rongjian Xu +6Visual Token PruningMultimodal Large Language Models

    City University of Hong Kong · Peking University · Huawei Technologies +1

  39. Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models

    Aug 7, 2026Minseok Kang, Hyunwoo Kim, Chanyoung Kim +3Visual Token PruningLarge Language Model Compression

    Department of Artificial Intelligence, Chung-Ang University, Seoul, Korea · School of Computer Science and Engineering, Soongsil University, Seoul, Korea · Department of Computer Science, Kookmin University, Seoul, Korea

  40. MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

    Aug 5, 2026Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa +2Model-Agnostic DefenseSelf-Supervised Vision Transformers

    Indian Institute of Technology Guwahati, India · Nanyang Technological University, Singapore · Prince of Songkla University, Phuket Campus

  41. A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization

    Aug 5, 2026Anadi Goyal, Nandish Chattopadhyay, Anupam Chattopadhyay +1Vision TransformerVisual Token Pruning

    Indian Institute of Technology Guwahati, Guwahati 781039, Assam, India · Nanyang Technological University, 50 Nanyang Ave, Singapore 639798

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

    Aug 5, 2026Chen Zhong, Xiao An, Zijie Wang +3Long Visual-Token SequencesRecent Vision-Language Models

    State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, China · Electronic Information School, Wuhan University, China

  43. Not All Redundant Tokens Are Alike: Analyzing Visual Token Pruning through Token Roles

    Aug 5, 2026Hyeonyu Kim, Sehwan Lim, Youngwon Choi +2Visual Token PruningLens

    Maum AI Inc., Republic of Korea

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

    Aug 4, 2026Yanning Hou, Jingyuan Zhang, Xiaoyun Wang +3Multimodal Anomaly DetectionVisual Token Pruning

    2National University of Defense Technology, Changsha, China · 1Anhui University, Hefei, China

  45. SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models

    Aug 4, 2026Yaozhi Wen, Jialong Guo, Zhenliang Ni +2Visual Token PruningRecent Vision-Language Models

    Huawei Technologies

  46. Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

    Aug 4, 2026Ahmed Amine Aliane, Nasredine Semmar, Hassina AlianeNeural Machine TranslationVisual Token Pruning

    Arabic Institute for Translation, Algiers, Algeria · CEA LIST, Paris-Saclay, France · CERIST, Algeria

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

    Aug 4, 2026Yuyao Sun, Tao Deng, Shuang Li +3Visual Token PruningRecent Vision-Language Models

    Beihang University · Shanghai EABOT Technology Co., Ltd.

  48. Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

    Aug 4, 2026Paribesh Regmi, Qingshuang Chen, Chi Zhang +3Visual Token PruningVideo-Language Models

    Amazon.com Services LLC

  49. GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models

    Aug 4, 2026Mengjie Zhang, Qihui Zhu, Tao Zhang +10Visual Token PruningVideo-Language Models

    University of Science and Technology of China He Fei, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center He Fei, China

  50. DiffPrune: differentiable information throttling for token pruning in vision-language models

    Aug 3, 2026Landi He, Mingde Yao, Shawn Young +1Visual Token PruningDifferentiable Physics

    Shenzhen University of Advanced Technology · CUHK MMLab, CPII under InnoHK

  51. ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

    Aug 3, 2026Zizhong Ding, Junxian Li, Kai Liu +4Visual Token PruningMultimodal Large Language Models

    Shanghai Jiao Tong University · Xidian University

  52. Pruned BPE: Post-training Visibility Pruning and Token Reallocation for Byte Pair Encoding

    Aug 1, 2026Kenny ShaoByte-Pair EncodingSubword Tokenization

    Department of Computer Science Florida International University

  53. Interpretability-Guided Soft Pruning of Attention Heads in Vision Transformers

    Jul 31, 2026Kamil Książek, Piotr Suszyński, Michał Jan Włodarczyk +2Self-Supervised Vision TransformersVision Transformer

    Centre for Credible Artificial Intelligence Warsaw University of Technology Warsaw, Poland · Faculty of Mathematics and Computer Science Jagiellonian University Krakow, Poland · University of Warsaw Warsaw, Poland

  54. WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

    Jul 30, 2026Haozhe Hu, Hao Wu, Peiran Yin +3Visual Token PruningLLM Inference Optimization

    Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Munich Center for Machine Learning, LMU Munich

  55. Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models

    Jul 30, 2026Jie Ma, Zhike Qiu, Jie Gao +4Visual Token PruningMultimodal Large Language Models

    Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University · School of Information Engineering, Xiamen Ocean Vocational College · Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Sino-Russian Research Center for Digital Economy

  56. LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM Inference

    Jul 30, 2026Feng Yang, Xinrui Ju, Keyang Zhang +6Visual Token PruningLLM Inference Optimization

    1City University of Hong Kong · 2Peng Cheng Laboratory

  57. Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference

    Jul 29, 2026Feixiang Liu, Qiang Qiu, Hao Zhang +1Visual Token PruningMultimodal Large Language Models

    State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences

  58. SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

    Jul 28, 2026Yuchen Wang, Qihui Zhu, Yang Liu +2Visual Token PruningLong Visual-Token Sequences

    MoE Key Lab of BIPC, NEL-BITA, University of Science and Technology of China, Hefei, China · ChangXin Memory Technologies, Hefei, China · APKL of BIIP, IAI, Hefei Comprehensive National Science Center, Hefei, China

  59. PathSelect: Sequential Token Selection for Whole Slide Pathology

    Jul 26, 2026Jingzhi Chen, Landi He, Zehong Chen +2Visual Token PruningDownstream Fine-Tuning

    Shenzhen University of Advanced Technology

  60. Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models

    Jul 26, 2026Yiming Zhong, Chang Nie, Caifeng ShanVisual Token PruningAudio-Visual Reasoning

    1Nanjing University