LVLM Pruning

LVLM: Large Vision-Language Model

Follow this topic Ask about this topic

Latest papers

39 papers7 papers in the last four weeks, up 75% on the four weeks before. 0.0% of all new papers.

RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models
Nov 4, 2026Dongjin Lee, Eunju Lee, Jinhee Jang +2Visual Token Pruning LVLM Pruning
Chung-Ang University, Seoul, Republic of Korea
BtsPruner: Role-Aware Visual Token Pruning for Large Vision-Language Models
Nov 3, 2026Zihao Qi, Zhibo Zhang, Miaoxin Zhang +2Visual Token Pruning LVLM Pruning
Nanjing University · Huazhong University of Science and Technology
SVD-Prune: Spectral Vision Token Pruning under Extreme Compression
Nov 1, 2026Yvon Apedo, Martyna Poreba, Michal Szczepanski +1Visual Token Pruning LVLM Pruning
Universit´e Paris-Saclay, Univ Evry, IBISC, 91020, Evry-Courcouronnes, France · Universit´e Paris-Saclay, CEA, List, F-91120 Palaiseau, France
LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models
Oct 27, 2026Rinyoichi Takezoe, Yaqian Li, Weiren Wang +6Visual Token Pruning LVLM Pruning
Li Auto Inc. Beijing, China · Li Auto Inc. Shanghai, China · Li Auto Inc. Hangzhou, China
SPAR: Structural Pruning and Action Recovery for Vision-Language-Action Models
Oct 19, 2026Shenli Zheng, Zhou Fang, Yuan Du +2Efficient VLA Model Inference LVLM Pruning
Nanjing University, Nanjing, China · Nanjing University of Information Science and Technology, Nanjing, China
Visual Sufficiency Landscapes: Understanding Query-Conditioned Reliability in Visual Token Pruning
Oct 18, 2026Zhenghan Li, Kexin Sun, Wei Zheng +3Visual Token Pruning LVLM Pruning
School of Software, Northwestern Polytechnical University, Xi’an 710129, China
Hierarchical and Query-Aware Visual Token Pruning for High-Resolution LVLMs
Oct 16, 2026Luther Wei, Ling Zou, Kang-Yang Huang +2Visual Token Pruning Efficient VLM Inference
Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan · MediaTek Inc., Hsinchu, Taiwan
How Much Can We Prune? Exploring the Performance Limits of Visual Token Pruning
Oct 13, 2026Janghoon Cho, Shubhankar Borse, Reza Pourreza +4Visual Token Pruning LVLM Pruning
Qualcomm AI Research∗
DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models
Oct 6, 2026Shuo Yang, Changbai Li, Linlin Yang +6Multimodal Large Language Models Token Pruning
Beihang University · Communication University of China · National University of Singapore
ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs
Sep 28, 2026Xu Li, Yuxuan Liang, Yi Zheng +6Efficient VLM Inference Large Vision-Language Models
College of Computer Science and Artificial Intelligence Fudan University, Shanghai, China
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
QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning
Sep 17, 2026Shengli He, Yongchao Liang, Roumeng He +4Multimodal Large Language Models Visual Token Pruning
Guizhou University · Shanghai Ocean University
StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models
Sep 12, 2026Hansen Zhang, Landi He, Mingde Yao +1Efficient VLM Inference Visual Token Pruning
Shenzhen University of Advanced Technology, Shenzhen, China · School of Computer Science, Nanjing University, Nanjing, China · CUHK MMLab, CPII under InnoHK, Hong Kong, China
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
S $^2$ Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models
Sep 1, 2026Yuanyuan Jia, Shunpu Tang, Qianqian YangEfficient VLM Inference Multimodal Large Language Models
College of Information Science and Electronic Engineering, Zhejiang University Hangzhou, China
An AI4AI Framework for Visual Token Pruning
Aug 7, 2026Zhen Liu, Wenli Huang, Wei Song +3Automated Algorithm Discovery Efficient VLM Inference
Xi’an Jiaotong University · Ningbo University of Technology · 3North China University of Technology +3
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
Aug 7, 2026Minseok Kang, Hyunwoo Kim, Chanyoung Kim +3Vision-Language Models Efficient VLM Inference
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
SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models
Aug 4, 2026Yaozhi Wen, Jialong Guo, Zhenliang Ni +2Efficient VLM Inference Structured Pruning
Huawei Technologies
DiffPrune: differentiable information throttling for token pruning in vision-language models
Aug 3, 2026Landi He, Mingde Yao, Shawn Young +1Vision-Language Models Efficient VLM Inference
Shenzhen University of Advanced Technology · CUHK MMLab, CPII under InnoHK
SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models
Jul 28, 2026Yuchen Wang, Qihui Zhu, Yang Liu +2Efficient Multimodal Inference Multimodal Large Language Models
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
Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
Jun 23, 2026Qitong Wang, Fan Du, Pranav Maneriker +2Efficient VLM Inference Egocentric Vision
Dolby Laboratories, Inc., 1275 Market St, San Francisco, California, 94103, USA · Department of Computer and Information Sciences at the University of Delaware, Newark, DE 19711, USA · Dolby Laboratories, Inc.
OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
May 28, 2026Geng Li, Guohao Chen, Ting Chen +6Efficient VLM Inference Large Vision-Language Models
1Nanyang Technological University (NTU)
AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference
May 28, 2026Yilin Feng, Ahmed Burak Gulhan, Mahmut Taylan KandemirLLM Pruning Vision-Language Models
The Pennsylvania State University
MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
May 25, 2026Aritra Dutta, Somak AdityaVision-Language Models Efficient VLM Inference
Indian Institute of Technology, Kharagpur
Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency
Apr 27, 2026Yiran Huang, Lukas Thede, Massimiliano Mancini +2Large Vision-Language Models Structured Pruning
Technical University of Munich, Germany · Munich Center for Machine Learning, Germany. · Helmholtz Munich, Germany. +3
Towards Joint Quantization and Token Pruning of Vision-Language Models
Apr 19, 2026Xinqing Li, Xin He, Xindong Zhang +3Vision-Language Models VLM Quantization
VCIP, College of Computer Science, Nankai University · School of Computer Science and Engineering, Tianjin University of Technology · OPPO Research Institute +3
Topology-Aware Layer Pruning for Large Vision-Language Models
Apr 14, 2026Pengcheng Zheng, Chaoning Zhang, Ya Wen +10LVLM Pruning Neural Network Pruning
University of Electronic Science and Technology of China · Kyung Hee University · Nota Inc. +2
Collaborative Multi-Mode Pruning for Vision-Language Models
Apr 3, 2026Zimeng Wu, Yunhong Wang, Donghao Wang +1LVLM Pruning Efficient VLM Inference
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China · School of Computer Science and Engineering, Beihang University, Beijing, China
QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
Apr 3, 2026Xinhao Wang, Zhonyu Xia, Zhiwei Lin +2Visual Token Pruning LVLM Pruning
Wangxuan Institute of Computer Technology, Peking University
IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
Apr 1, 2026Dong-Jae Lee, Sunghyun Baek, Junmo KimEfficient VLM Inference Large Vision-Language Models
KAIST, South Korea

Nov 4, 2026J/K move · Enter open · S save

RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models

Dongjin Lee, Eunju Lee, Jinhee Jang, Yoonji Lee+1

Chung-Ang University, Seoul, Republic of Korea

Visual Token Pruning LVLM Pruning Vision-Language Models

Open paper AskPDF arXiv

Large vision-language models (LVLMs) have recently been extended to handle multiple input images, but this extension dramatically increases the visual token budget, making visual-token pruning not merely an efficiency option but a practical necessity. Existing visual-token pruning methods, primarily designed for the single-image setting, rely on attention-derived saliency signals to estimate per-token importance. However, this attention-centric design transfers poorly to the multi-image regime: it causes substantial performance degradation on multi-image benchmarks, suffers from strong positional bias, and loses discriminative attention signals as the number of input images increases. To test whether attention-selected tokens are truly important for multi-image reasoning, we conduct two complementary causal probes Leave-One-In and Leave-One-Deletion, which measure token importance by restoring individual tokens to a zeroed visual sequence or removing them from the full sequence. Attention-based pruners provide only marginal gains over random selection, showing that attention is a weak proxy for visual-token importance in multi-image reasoning. Motivated by this gap, we propose Relation and Information Aware Pruning (RI-Prune), a training-free, attention-free pre-decoder selector for multi-image visual token pruning. RI-Prune scores each visual token using a z-normalized combination of three signals computed from projector outputs: query relevance, cross-image correspondence with compact per-image prototypes, and intra image representativeness. By integrating these signals, RI-Prune performs balanced per-image Top-K selection to preserve information across input images. Across multiple multi-image benchmarks and three LVLM backbones, RI-Prune achieves a stronger trade-off between token reduction and task performance than prior pruning methods, particularly under aggressive token budgets.