Visual Token Compression

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 67% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 184

All topics

An Efficient Token Compression Framework for Visual Object Tracking
May 8, 2026Weijing Wu, Qihua Liang, Bineng Zhong +3Visual Object Tracking Efficient ViTs
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, China · Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, China · University Engineering Research Center of Educational Intelligent Technology, Guangxi Normal University, Guilin, 541004, China +1
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
May 8, 2026Zuojin Tang, Shengchao Yuan, Xiaoxin Bai +4Action-Conditioned World Models Efficient VLA Models
Zhejiang University · Central South University · Harbin Institute of Technology +2
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
May 8, 2026Hang Wu, Sherin Mary Mathews, Yujun Cai +2Streaming Video Understanding Efficient VLM Inference
University of California, Merced · US Bank · University of Queensland
TTF: Temporal Token Fusion for Efficient Video-Language Model
May 8, 2026Simin Huo, Ning LIToken Merging Efficient VLM Inference
Shanghai Jiao Tong University
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
May 7, 2026Roy Xie, Dan Friedman, Donghan Yu +7Document Understanding Tool Use in VLMs
Apple · Duke University
Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction
May 7, 2026Zecheng Tang, Jiaye Fu, Qiankun Gao +53D Reconstruction Efficient ViTs
School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China
Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
May 7, 2026Bowen Zheng, Yihong Luo, Tianyang HuImage Tokenization Visual Tokenization
The Chinese University of Hong Kong, Shenzhen · Hong Kong University of Science and Technology
VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading
May 7, 2026Cheng Xu, Xiaofeng Hou, Jiacheng Liu +1Expert Offloading Vision-Language Models
Shanghai Jiao Tong University Minhang Qu, Shanghai, China
VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
May 7, 2026Kuanwei Lin, Wenhao Zhang, Ge LiEfficient VLM Inference Long-Video Understanding
School of Electronic and Computer Engineering, Peking University
Visual Text Compression as Measure Transport
May 6, 2026Lv Tang, Tianyi Zheng, Yang Liu +2Efficient VLM Inference Visual Tokenization
University of Alberta1 · vivo Mobile Communication Co., Ltd2 · Tsinghua University3
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
May 6, 2026Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9Image Tokenization Autoencoders
University of Texas, Austin · University of Washington · 3Stanford University +3
CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative Decoding
May 4, 2026Yuanyuan Jia, Shunpu Tang, Qianqian YangEfficient VLM Inference Edge Computing
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
Make Your LVLM KV Cache More Lightweight
May 1, 2026Xihao Chen, Yangyang Guo, Roger ZimmermannKV Caching Efficient VLM Inference
Integrative Sciences and Engineering Programme, National University of Singapore · School of Computing, National University of Singapore
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
May 1, 2026Wenda Chu, Bingliang Zhang, Jiaqi Han +4Image Tokenization Visual Tokenization
ByteDance Seed · California Institute of Technology · Stanford University
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
May 1, 2026Ben Wan, Yan Feng, Zihan Tang +4Efficient VLM Inference Optical Character Recognition
Shanghai Jiao Tong University · University of Science and Technology of China · Tsinghua University
Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
Apr 29, 2026Cyril Shih-Huan Hsu, Wig Yuan-Cheng Cheng, Chrysa PapagianniEfficient VLM Inference Edge Computing
Informatics Institute, University of Amsterdam, The Netherlands. · Open-EP Community, Taoyuan City 330049, Taiwan (R.O.C.).
VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
Apr 27, 2026Maitreya Patel, Jingtao Li, Weiming Zhuang +2Image Tokenization Visual Tokenization
Arizona State University · SonyAI · 3Work partially done while at SonyAI. Maitreya is now at Adobe.
T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability
Apr 20, 2026Savya Khosla, Sethuraman T, Aryan Chadha +2VLM Adaptation Open-Vocabulary Semantic Segmentation
University of Illinois Urbana-Champaign
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
Apr 20, 2026Han Li, Zehao Huang, Jiahui Fu +2Visual Token Pruning Visual Token Compression
Beihang University · Zhongguancun Academy
EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
Apr 18, 2026Jiafei Song, Fengwei Zhou, Jin Qu +7Efficient Multimodal Inference Multimodal Large Language Models
OPPO CTG
Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
Apr 17, 2026Yang ShanglinVisual Token Pruning Visual Token Compression
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Apr 16, 2026Xuanyi Liu, Chunan Yu, Deyi Ji +63D ViTs Streaming 3D Reconstruction
KOKONI 3D, Moxin Technology · Nanjing University of Science and Technology · University of Science and Technology of China +4
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
Apr 16, 2026Mingqian Ji, Shanshan Zhang, Jian YangMulti-View 3D Object Detection Efficient ViTs
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology · PCA Lab, School of Intelligence Science and Technology, Nanjing University
DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
Mar 15, 2026Bingzhou Li, Tao HuangAudio-Visual Understanding Efficient Multimodal Inference
Shanghai Jiao Tong University, Shanghai, China · Tongji University, Shanghai, China
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Mar 7, 2026Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17Token Merging Image Segmentation
University of Stuttgart · DFKI · Max Planck Research School +10
Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
Mar 5, 2026Jiaqi Li, Shuntian Zheng, Yixian Shen +4Temporal Video Grounding Vision-Language Grounding
University of Warwick, Coventry CV4 7AL, United Kingdom · University of Amsterdam, Amsterdam 1012 WX, Netherlands · Amazon AGI, The United States of America
Stateful Token Reduction for Long-Video Hybrid VLMs
Feb 27, 2026Jindong Jiang, Amala Sanjay Deshmukh, Kateryna Chumachenko +7Efficient VLM Inference Video-Language Models
NVIDIA
AFFMAE: Scalable Vision Pre-Training for High-Resolution Microscopy Segmentation on Desktop Hardware
Feb 18, 2026David Smerkous, Zian Wang, Behzad NajafianMasked Autoencoders Self-Supervised Pre-Training
Department of Laboratory Medicine & Pathology, University of Washington, Seattle WA, USA · Electrical Engineering & Computer Science, Oregon State University, Corvallis, OR, USA · Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle WA, USA
LGQ: Learnable Geometric Quantization for Image Tokenization
Feb 17, 2026Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton +2Image Tokenization Vector Quantization
Luddy School of Informatics, Computing and Engineering, Indiana University Bloomington · Department of Computer Science, University of Illinois Springfield · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
Jan 29, 2026Jiahao Huo, Yu Huang, Yibo Yan +7Multimodal Embedding Multi-Vector Retrieval
The Hong Kong University of Science and Technology (Guangzhou) · Alibaba Cloud Computing · The Hong Kong University of Science and Technology +1

May 8, 2026, cs.CVJ/K move · Enter open · S save

An Efficient Token Compression Framework for Visual Object Tracking

Weijing Wu, Qihua Liang, Bineng Zhong, Haiying Xia+2

Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, 541004, China · Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, 541004, China · University Engineering Research Center of Educational Intelligent Technology, Guangxi Normal University, Guilin, 541004, China+1

Visual Object Tracking Efficient ViTs Visual Token Pruning Visual Token Compression

Open paper AskPDF arXiv

Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many contemporary Transformer-based trackers leverage a larger number of historical template frames to capture richer spatio-temporal cues. However, this strategy leads to a massive number of input visual tokens. This creates two critical issues: it imposes a quadratic computational burden and can also degrade the tracker's overall performance. To bridge this gap, we propose a compress-then-interact tracking framework, ETCTrack, that learns to efficiently compress template tokens from historical template frames into a robust target representation, moving beyond handcrafted rules. Our method first employs the Adaptive Token Compressor to dynamically construct compact yet highly discriminative template tokens by filtering out redundant visual tokens. These refined template tokens are then processed by our Hierarchical Interaction Encoder to achieve a deep, adaptive interaction with the search features. Refined search features ensure subsequent precise target localization. Experiments on seven benchmarks demonstrate that our method outperforms current state-of-the-art trackers. ETCTrack-B224 reduces the number of template tokens by 60%, leading to a 21.4% reduction in MACs with only a 0.4% drop in accuracy. The source code are available at https://github.com/PJD-WJ/ETCTrack.

Momentum

Related topics

Latest papers 184