Token Compression

Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 81

All topics
CardsList

  1. VETO: Video Efficient Token Optimization for Vision Language Models

    Oct 1, 2026Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen +1Token CompressionVideo-Language Models

    National Taiwan University · NVIDIA

  2. Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization

    Oct 1, 2026Jeeyoung Yun, Seohwan Yun, Sungwoong KimNeural Speech CodecsAudio Tokenizers

    Korea University, Seoul, Republic of Korea

  3. ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models

    Oct 1, 2026Lianjun Liu, Shipeng Li, You Huang +5Token CompressionLocalized Lora-Moe

    Hainan University, Haikou, China · Xiamen University, Xiamen, China · Zhejiang Normal University, Jinhua, China

  4. CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding

    Sep 30, 2026Yulong Liu, Xiaotian Han, Junyuan Shang +6Vision EncodersToken Compression

    ERNIE Team, Baidu Inc. · The Hong Kong University of Science and Technology · Institute of Automation, Chinese Academy of Sciences (CASIA)

  5. DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

    Sep 30, 2026Xu Huang, Ye Huang, Zijun Liao +6Generative Image CompressionToken Compression

    Peking University · Singapore University of Technology and Design

  6. Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models

    Sep 30, 2026Shilinlu Yan, Bowen Chen, Yuechen Zhang +3Token CompressionVision Encoders

    Beijing University of Posts and Telecommunications · Jiangnan University · Nanyang Technological University +1

  7. Aperture: Merge-Consistent Rotary States for Compressed Tokens

    Sep 29, 2026Yuhao Du, Shunian ChenToken CompressionRotary Position Embedding

    The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute

  8. Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline

    Sep 28, 2026Xiao Zhang, Wang Zeng, Sheng Jin +3Token CompressionStrong Baseline

    School of Computer Science and Engineering, Central South University · SenseTime Research and Tetras.AI

  9. Beyond Selection: Token Parameterization for Extreme Visual Token Compression

    Sep 28, 2026Rui Zhong, Yu Li, Zheyu Yan +1Token CompressionData Compression Methods

    Zhejiang University

  10. Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models

    Sep 28, 2026Qiankun Li, Yuechen Zhang, Bowen Chen +4Token CompressionInference Cost

    Nanyang Technological University · Beijing University of Posts and Telecommunications

  11. Resolution as a First-Class Decision: Task-Conditioned Routing for Efficient Multimodal Large Language Models

    Sep 28, 2026Zhiqiang Xia, Yang Li, Xinyuan Zhang +5Multimodal Large Language ModelsToken Compression

    Xiaomi Corporation, Beijing, China

  12. CoViST: Visual Token Compression via Composable States

    Sep 27, 2026Qi Zhang, Xiandong Meng, Ronggang Wang +1Token CompressionData Compression Methods

    Peng Cheng Laboratory Shenzhen, China · Peking University Shenzhen Graduate School Peking University Beijing, China

  13. Compressing AI Traffic: Standardized Neural Network Coding of Visual-Token Representations in Split Vision-Language Inference

    Sep 1, 2026Reza Heidari, Hamed R. Tavakoli, Juho KannalaToken CompressionVision Encoders

    Aalto University, Nokia Technologies · Nokia Technologies · Espoo, Finland +1

  14. Token-Oriented Semantic Communication with Pretrained Vision Transformers

    Aug 26, 2026Jiwoong Im, Minwoo Kim, Jaeho Lee +2Token CompressionSelf-Supervised Vision Transformers

    Department of Electrical Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, South Korea

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

    Aug 21, 2026Zhuoyuan Li, Rui Zhao, Jin Wang +5Token CompressionGoal-Conditioned Dynamic Manipulation

    Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798 · Bytedance Inc. +2

  16. Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression

    Aug 10, 2026Jingbo Wen, Liang He, Mingyu Cao +4Long Visual-Token SequencesToken Compression

    1The University of Sydney · 2Tongji University · University of Surrey +3

  17. Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding

    Aug 9, 2026Donghui Feng, Fengxi Zhang, Changsheng Gao +6Token CompressionVision Transformer

  18. Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

    Aug 9, 2026Yu Wang, Shengyao Zhuang, Xueguang Ma +4RetrieversTransformer Architectures

    University of Utah · 2The University of Queensland · University of Waterloo +1

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

    Aug 5, 2026Jiuhe Qu, Yingping Liang, Ying Fu3D Scene UnderstandingToken Compression

    Beijing Institute of Technology Beijing, China

  20. OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

    Aug 4, 2026Wanshun Su, Yang Shi, Feihu Liu +10Token CompressionOmni-Modal

    Northwestern Polytechnical University · Peking University · Alibaba Group +1

  21. Decoupling semantics from vision: A framework for faithful visual-text compression evaluation

    Aug 3, 2026Yonghan Gao, Zehong Chen, Lijian Xu +3Token CompressionMultimodal Large Language Models

    Shenzhen University of Advanced Technology · Shenzhen Technology University

  22. Allocation Before Ranking: Decoupled Token Compression for OmniLLMs

    Aug 3, 2026Zhenghui Guo, Yilin Yang, Yuanbin Man +5Token CompressionData Compression Methods

    Department of Computer Science, University of Houston · Department of Computer Science and Engineering, The University of Texas at Arlington

  23. CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

    Aug 3, 2026Yu Chen, Xiaohong Li, Xiaole Wang +3Token CompressionVideo-Language Models

    1Evermind · 2Shanda Group · 3Peking University

  24. Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Everywhere

    Aug 2, 2026Jiayang He, Tianling Xu, Diancheng Kang +4Token CompressionVideo Compression

    Southern University of Science and Technology · Imperial College London · Jilin University

  25. 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

    Aug 2, 2026Changwoo Baek, Kyeongbo KongToken Compression3D Representation

    Department of Electrical and Electronics Engineering, Pusan National University, Busan, Republic of Korea

  26. Think in Sets for Streaming Video Token Compression

    Aug 2, 2026Moxu Duan, Jingwen Fu, Yuwang WangToken CompressionTask-Aware Compression

    Beijing Jiaotong University · Zhongguancun Academy · Tsinghua University

  27. TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference

    Aug 1, 2026Ning Li, Xinyu Wang, Xin Yuan +3Mixture-Of-Expert InferenceToken Compression

    School of Artificial Intelligence, University of Science and Technology Beijing, China · School of Computer Science and Technology, Harbin Institute of Technology, Heilongjiang, China · School of Ocean Engineering, Harbin Institute of Technology, Heilongjiang, China +2

  28. ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression

    Jul 31, 2026Renjie Liang, Zijian Xu, Jinqian Pan +6Token CompressionCone-Beam Computed Tomography

    University of Florida, Gainesville, FL, USA · University of Southern California, Los Angeles, CA, USA · National University of Singapore, Singapore

  29. OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

    Jul 28, 2026Haoyang Huang, Wenjie Huang, Tianqi Xu +14Token CompressionAudio Tokenizers

    Zhejiang University · Qwen Application, Alibaba · Carnegie Mellon University +2

  30. Joint Optimization for Greedy Longest-match Tokenization

    Jul 25, 2026Adhiraj Singh, Deepanshu Mody, Ghina Al Shdaifat +4Byte-Pair EncodingToken Compression

    Center for Data Science, New York University New York, NY, USA · Kensho Technologies Cambridge, MA, USA

  31. WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

    Jul 25, 2026Yuhui Zeng, Wang Chen, Jinfa Huang +5Token CompressionVideo Compression

    Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Department of Computer Science, University of Rochester, Rochester, NY, USA

  32. OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models

    Jul 25, 2026Jinsen Su, Yongdong Luo, Yuexiao Ma +3Token CompressionOmni-Modal

    Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Institute of Artificial Intelligence, Xiamen University, Xiamen, China · School of Informatics, Xiamen University, Xiamen, China +1

  33. Progressive Cramming: Reliable Token Compression and What It Reveals

    Jul 23, 2026Dmitrii Tarasov, Timofei Lashukov, Elizaveta Goncharova +1Token CompressionData Compression Methods

    FusionBrain Lab, AXXX, Moscow, Russia · HSE University, Moscow, Russia · Artificial Intelligence Institute, Innopolis University, Innopolis, Russia

  34. Out of Sight, Still in Mind: Token Compression for Omni-LLMs

    Jul 23, 2026Suho Yoo, Youngjoon Jang, Hyebin Cho +1Token CompressionOmni-Modal

    KAIST · VGG, University of Oxford

  35. Visual Token Compression Enhances Robustness of MLLMs

    Jul 21, 2026Shishen Gu, Jiequan Cui, Wenbo Hu +3Visual Token PruningRecent Vision-Language Models

    Hefei University of Technology · Hefei, China

  36. VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression

    Jul 14, 2026Yupeng Zheng, Kai Zou, Bin Liu +1Token CompressionData Compression Methods

    Anhui Province Key Laboratory of Digital Security, University of Science and Technology of China Hefei, China

  37. GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models

    Jul 10, 2026Guohuan Xie, Mengqi Lei, Chuan Shi +3Token CompressionGeogs-Slam

    BNRist, THUIBCS, BLBCI, School of Software, Tsinghua University · Yangtze Delta Region Institute, Tsinghua University · Beijing University of Posts and Telecommunications, Beijing, China

  38. OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

    Jul 3, 2026Shijie Cao, Qingyu Zhang, Boxi Yu +6Token CompressionAudio-Visual Reasoning

    School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Limerick +1

  39. STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation

    Jul 3, 2026Syed Ariff Syed Hesham, Yun Liu, Guolei Sun +4Spatial TokensToken Compression

    School of EEE, Nanyang Technological University, Singapore · Institute for Infocomm Research, A*STAR, Singapore · VCIP, CS, Nankai University, Tianjin, China +4

  40. When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression

    Jul 2, 2026Tien-Phat Nguyen, Ngai-Man CheungToken CompressionSelf-Supervised Vision Transformers

    Temasek Laboratories, Singapore University of Technology and Design, Singapore

  41. MinGram: A Minimalist Unigram Tokenizer with High Compression and Competitive Morphological Alignment

    Jun 25, 2026Sander LandUnigram TokenizerToken Compression

    Writer, Inc.

  42. DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception

    Jun 24, 2026Tianle Zhu, Haohua Que, Handong Yao +2V2XToken Compression

    University of Georgia, Athens, GA, USA. · University of the Arts London, London, UK.

  43. AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

    Jun 23, 2026Yijing Chen, Wenhui Tan, Xiaoyi Yu +7Audio-Visual ReasoningLarge Audio Language Models

    Gaoling School of Artificial Intelligence, Renmin University of China · Huawei Inc.

  44. CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents

    Jun 16, 2026Jiaqi Chen, Yongqin Zeng, Shaoshen Chen +4Peak MemoryLong-Term Memory

    Shenzhen International Graduate School, Tsinghua University · Peng Cheng Laboratory · Shandong Analysis and Test Center, Qilu University of Technology, Jinan, China +1

  45. HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing

    Jun 11, 2026Haoran You, Yotam Nitzan, Lingzhi Zhang +7Diffusion-Based Image EditingImage Editing

    Adobe ART AI Lab · Adobe Research

  46. Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models

    Jun 11, 2026Jialin Gan, Xin Qiu, Guangzhe Chen +1Token CompressionTime Series

    Zhejiang University · Harbin Institute of Technology · Shandong University

  47. Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

    Jun 10, 2026Changyue Wang, Weihang Su, Qingyao Ai +5LLM Inference OptimizationToken Compression

    Department of Computer Science and Technology, Tsinghua University

  48. Planning-aligned Token Compression for Long-Context Autonomous Driving

    Jun 5, 2026Zhixuan Liang, Yuxiao Chen, Yurong You +12Token CompressionAutonomous Driving

    NVIDIA Research · School of Computing and Data Science, The University of Hong Kong

  49. Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines

    Jun 2, 2026Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum +3Token CompressionToken-Level Entropy

    1VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · 2Quantum and Assistive Technologies Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

  50. InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models

    Jun 1, 2026Xinxin Liu, Shiwei Gan, Xiao Liu +3Token CompressionVideo-Language Models

    State Key Laboratory of Novel Software Technology, Nanjing University Nanjing 210023, China

  51. EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models

    Jun 1, 2026Hongyu Lu, Feng Zhang, Wenwei Jin +5Token CompressionVision Encoders

    Harbin Institute of Technology · Xiaohongshu · Fudan University

  52. ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs

    May 30, 2026Yiling Gao, Hongchen Wei, Zhenzhong ChenToken CompressionDataset Distillation

    School of Remote Sensing and Information Engineering, Wuhan University

  53. PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding

    May 28, 2026Selim Kuzucu, Alessio Tonioni, Vasile Lup +3Token CompressionRecent Vision-Language Models

    Max Planck Institute for Informatics, SIC · Google · Technical University of Munich

  54. EarlyTom: Early Token Compression Completes Fast Video Understanding

    May 28, 2026Hesong Wang, Xin Jin, Lu Lu +4Token CompressionVision Encoders

    Zhejiang University · Westlake University · Alibaba Cloud Computing

  55. Accelerating Constrained Decoding with Token Space Compression

    May 28, 2026Michael Sullivan, Alexander KollerToken CompressionContext-Free Grammars

    Department of Language Science and Technology Saarland Informatics Campus Saarland University, Saarbrücken, Germany

  56. BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression

    May 28, 2026Yuquan Bi, Baosheng Yu, Yingke Lei +5WatermarksToken Compression

    School of Cyber Science and Engineering, Southeast University, Nanjing, China · Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore · College of Electronic Engineer, National University of Defense and Technology, Hefei, 230000, China +5

  57. AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

    May 26, 2026Haoran Zhang, Zhaohua SunLarge Language Model AgentsTask-Aware Compression

    AI Agent Technologies (Hong Kong) Limited · Department of Mechanical Engineering, The University of Hong Kong

  58. Locality Matters for Training-Free Audio Token Compression in Audio-Language Models

    May 24, 2026Jiale Luo, Xiaoyu Liang, Haoji HuAudio UnderstandingToken Compression

    1Zhejiang University

  59. Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention

    May 22, 2026Bingtian Qiao, Yue Shi, Yingjie Zhou +3Real-World Image Super-ResolutionImage Restoration

    Shanghai Jiao Tong University · Fuzhou University · Shanghai AI Laboratory

  60. DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs

    May 19, 2026Minyoung Park, Taehun Kong, Sangjun AhnToken CompressionVideo Compression

    LG Electronics, Seoul, South Korea