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 186

All topics

Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning
Oct 8, 2026Yicheng Xue, Han Wu, Jufeng Yang +4VLM Reasoning Efficient Multimodal Inference
City University of Hong Kong · Zhejiang University · Peking University +2
V-CoLA: Vision Token Compression with Linear Attention
Oct 8, 2026Hao Jiang, Yiru Mao, Tianpeng Bu +9Visual Token Compression Efficient VLM Inference
Alibaba Cloud Computing, Alibaba Group
QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation
Oct 7, 2026Yucheng Mao, Zeyuan Chen, Xiaojun Shan +4Visual Tokenization Autoregressive Image Generation
University of California, San Diego
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Oct 7, 2026Shuailong Wang, Xinyu Lyu, Shengming Yuan +3Visual Token Pruning VLM Robustness
University of Electronic Science and Technology of China, Chengdu, China · Southwestern University of Finance and Economics, Chengdu, China · Tongji University, Shanghai, China +1
Adaptive Visual Token Reduction for Accelerated Image Understanding
Oct 7, 2026Seyoung Jeong, Jong Pil Yun, Sang Jun LeeEfficient VLM Inference Visual 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
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Oct 6, 2026Yuan Feng, Qize Yang, Ruizhe Chen +9Efficient Multimodal Inference Multimodal Large Language Models
University of Science and Technology of China · Alibaba Token Hub, Alibaba Group · The Chinese University of Hong Kong +1
Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMs
Oct 6, 2026Donghyun Han, Jangho Park, Yuseok BaeEfficient VLM Inference Visual Token Pruning
ETRI, South Korea · Kyung Hee University, South Korea
Level-of-Token Diffusion
Oct 5, 2026Kiyohiro Nakayama, Brian Chao, Jan Ackermann +5Video Diffusion Models Diffusion Transformer
Stanford University · Google
VETO: Video Efficient Token Optimization for Vision Language Models
Oct 1, 2026Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen +1Efficient VLM Inference Large Vision-Language Models
National Taiwan University · NVIDIA
CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
Sep 30, 2026Yulong Liu, Xiaotian Han, Junyuan Shang +6Video Understanding Efficient VLM Inference
ERNIE Team, Baidu Inc. · The Hong Kong University of Science and Technology · Institute of Automation, Chinese Academy of Sciences (CASIA)
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
Sep 30, 2026Xu Huang, Ye Huang, Zijun Liao +6Autoencoders Diffusion-Based Image Generation
Peking University · Singapore University of Technology and Design
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
Sep 30, 2026Shilinlu Yan, Bowen Chen, Yuechen Zhang +3VLM Robustness Adversarial Attacks on VLMs
Beijing University of Posts and Telecommunications · Jiangnan University · Nanyang Technological University +1
Task-Oriented Visual Feature Compression via Residual Vector Quantization for Device-Edge Multimodal Inference
Sep 29, 2026Luning Pang, Cheng Yuan, Jiawei Shao +2Efficient Multimodal Inference Visual Token Compression
Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China · Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing 100033, China
Representation Dynamics Reveal Semantic Saliency and Similarity for Visual Token Pruning in MLLMs
Sep 29, 2026Weixuan Li, Zikun Zhou, Xinyi Zhuang +4Efficient VLM Inference Visual Token Pruning
Harbin Institute of Technology, Shenzhen · Shenzhen Loop Area Institute
Aperture: Merge-Consistent Rotary States for Compressed Tokens
Sep 29, 2026Yuhao Du, Shunian ChenRotary Positional Embeddings Visual Token Merging
The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute
NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generation
Sep 29, 2026Jiawei Zhang, Shuhao Liu, Rong Huang +4Autoregressive Image Generation Visual Token Compression
North China Electric Power University · University of Science and Technology of China · Stanford University
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
Sep 29, 2026FangZhi Zhong, Xuerui Qiu, Yuqi Pan +4Efficient VLM Inference VLM Reasoning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Zhongguancun Academy +1
Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline
Sep 28, 2026Xiao Zhang, Wang Zeng, Sheng Jin +3Video Understanding Video-Language Models
School of Computer Science and Engineering, Central South University · SenseTime Research and Tetras.AI
Beyond Selection: Token Parameterization for Extreme Visual Token Compression
Sep 28, 2026Rui Zhong, Yu Li, Zheyu Yan +1Efficient VLM Inference Large Vision-Language Models
Zhejiang University
Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models
Sep 28, 2026Qiankun Li, Yuechen Zhang, Bowen Chen +4VLM Robustness Adversarial Attacks on VLMs
Nanyang Technological University · Beijing University of Posts and Telecommunications
Resolution as a First-Class Decision: Task-Conditioned Routing for Efficient Multimodal Large Language Models
Sep 28, 2026Zhiqiang Xia, Yang Li, Xinyuan Zhang +5Efficient Multimodal Inference Efficient VLM Inference
Xiaomi Corporation, Beijing, China
When Text Matters: Design Principles for Visual Token Pruning in Vision-Language Model
Sep 28, 2026Minchan Kang, Kyeonghye Park, Seoyoung Cho +2Efficient VLM Inference Visual Token Pruning
Korea Advanced Institute of Science and Technology (KAIST) · Hanbat National University
CoViST: Visual Token Compression via Composable States
Sep 27, 2026Qi Zhang, Xiandong Meng, Ronggang Wang +1Vision-Language Models Efficient VLM Inference
Peng Cheng Laboratory Shenzhen, China · Peking University Shenzhen Graduate School Peking University Beijing, China
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Sep 26, 2026Junxian Li, Ruixuan Yang, Tianao Zhang +3Efficient VLM Inference VLM Distillation
Shanghai Jiao Tong University · Xi’an Jiaotong University · University of Cambridge +1
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
Sep 21, 2026Guangchuan Lv, Dianxing Shi, Dingjie FuEfficient VLM Inference Large Vision-Language Models
Northeastern University · Beihang University · Huazhong University of Science and Technology
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
Sep 15, 2026Haoyu Guo, Yuan Feng, Junlin Lv +3Efficient VLM Inference Long-Video Understanding
School of Biomedical Engineering, University of Science and Technology of China · Data Darkness Lab, MIRACLE Center, Suzhou Institute for Advanced Research · China +1
SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering
Sep 14, 2026Davit Soselia, Joseph JaJa, Amitabh Varshney3DGS Compression Language-Embedded 3DGS
University of Maryland, College Park, MD, USA
TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents
Sep 9, 2026Yuhao Wang, Mu Qiao, Xindong Zhang +3KV-Cache Compression Visual Token Pruning
Dalian University of Technology · OPPO Research Institute · The Hong Kong Polytechnic University
Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization
Sep 2, 2026Qingchan Zhu, Weihang You, Hanqi Jiang +3Efficient VLM Inference Visual Token Pruning
School of Computing, University of Georgia · College of Engineering, Northeastern University
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
Sep 1, 2026Mingda Lin, Weijie Wang, Zeyu Zhang +73D Reconstruction 3D Representation Learning
1Zhejiang University · 2Monash University · University of Adelaide

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

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

Yicheng Xue, Han Wu, Jufeng Yang, Minjing Dong+3

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

VLM Reasoning Efficient Multimodal Inference Memory-Augmented VLMs Visual Token Compression Visual Token Pruning

Open paper AskPDF arXiv

Processing long visual token sequences from high-resolution images makes multi-step reasoning computationally expensive for multimodal Large Language Models (MLLMs). Existing one-shot pruning and aggregation methods compress visual tokens into a fixed context before decoding. However, visual evidence needs can shift as reasoning unfolds, making it difficult for a fixed compressed context to retain all the details needed across stages. To address this challenge, we propose ViMoD, a lightweight framework that maintains a compact visual context while preserving access to original fine-grained evidence as reasoning needs evolve. Deformable Aggregation of Region-wise Tokens (DART) learns content-adaptive groups and aggregation capacities, constructing compact Coarse representations linked to recoverable original Fine tokens. Temporal Routing for Adaptive Contextual Evidence (TRACE) integrates decoding history to anticipate upcoming evidence needs and select, retain, or replace active Fine-token groups. Selected Fine tokens augment the persistent Coarse context in the frozen backbone, enabling stage-specific evidence access without continuously attending to all visual tokens. On Qwen3-VL-4B, ViMoD outperforms all evaluated baselines on all eight reasoning benchmarks at a 20% target visual token budget, improving the mean normalized score by 39.0% over the strongest evaluated one-shot baseline. These gains are achieved with only 0.0546% additional trainable parameters relative to the frozen backbone.

Momentum

Related topics

Latest papers 186