Visual token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instructions and fine-grained queries. In this paper, we investigate this failure and identify two underlying bottlenecks: the widespread dispersion of textual noise that corrupts dense cross-modal scoring, and the feature fragmentation inherent to standard token selection. To address these issues, we propose Entropy-Aware Dense Pruning (EADP), a framework that reformulates pruning as a structured compression problem. EADP first leverages statistical entropy to quantify and filter out textual noise, yielding a robust, fine-grained instruction relevance score. Subsequently, instead of naive Top-K selection, EADP casts token selection as a submodular maximization problem with a spatial prior, explicitly ensuring a holistic and non-redundant visual representation. Extensive experiments demonstrate that EADP improves the accuracy-efficiency trade-off of VLMs, robustly preserving fine-grained visual cues under strict token budgets while achieving SoTA performance on challenging multimodal benchmarks.
University of Tennessee（田纳西大学）；Oak Ridge National Laboratory（橡树岭国家实验室）；Sun Yat-Sen University（中山大学）
Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning. In this work, we investigate the channel pruning from a new perspective with statistical modeling. We hypothesize that the number of filters at a certain layer reflects the level of 'redundancy' in that layer and thus formulate the pruning problem from the aspect of redundancy reduction. Based on both theoretic analysis and empirical studies…
The University of Tennessee Knoxville（田纳西大学诺克斯维尔分校）；Sun Yat-sen University（中山大学）
Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact architectures. In this study, we claim that identifying structural redundancy plays a more essential role than finding unimportant filters, theoretically and empirically. We first statistically model the network pruning problem in a redundancy reduction perspective and find that pruning in the layer(s) with the most structural redundancy outperfor…
Locality-Aware Redundancy Pruning for LLM Depth Compression
University of Southern California（美国南加州大学）；Neural Superintelligence Lab, MODULABS（MODULABS神经超级智能实验室）；Seoul National University（首尔国立大学）；Inha University（釜山大学）
Filter Pruning For CNN With Enhanced Linear Representation Redundancy
Tianjin Normal University（天津师范大学）；Southwestern University of Finance and Economics（西南财经大学）；University of Electronic Science and Technology of China（电子科技大学）
Beijing University of Posts and Telecommunications（北京邮电大学）
Filter pruning method introduces structural sparsity by removing selected filters and is thus particularly effective for reducing complexity. Previous works empirically prune networks from the point of view that filter with smaller norm contributes less to the final results. However, such criteria has been proven sensitive to the distribution of filters, and the accuracy may hard to recover since the capacity gap is fixed once pruned. In this paper, we propose a novel filter pruning method called Asymptotic Soft Cluster Pruning (ASCP), to identify the redundancy of network based on the similar…
The existence of redundancy in Convolutional Neural Networks (CNNs) enables us to remove some filters/channels with acceptable performance drops. However, the training objective of CNNs usually tends to minimize an accuracy-related loss function without any attention paid to the redundancy, making the redundancy distribute randomly on all the filters, such that removing any of them may trigger information loss and accuracy drop, necessitating a following finetuning step for recovery. In this paper, we propose to manipulate the redundancy during training to facilitate network pruning. To this e…
MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
Chinese University of Hong Kong（香港中文大学）；Westlake University（西湖大学）；Southern Medical University（南方医科大学）；Jiangnan University（江南大学）；Dalian University of Technology（大连理工大学）；Shanghai Jiao Tong University（上海交通大学）；University of Copenhagen（哥本哈根大学）
SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beihang University（北京航空航天大学）
ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Carizon；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capacity, and then prune unimportant learning units (filters and neurons) during training to improve model compactness. We argue it is unnecessary to introduce redundancy at the beginning of the training but then reduce redundancy for the ultimate inference model. In this paper, we propose a Continuous Growth and Pruning (CGaP) scheme to minimize the redundancy from the beginning. CGaP starts the training from a small ne…
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction. Although extremely effective, most works are based only on quantitative characteristics of the convolutional filters, and highly overlook the qualitative interpretation of individual filter's specific functionality. In this work, we interpreted the functionality and redundancy of the convol…
Syracuse University（雪城大学）；Peking University（北京大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院麻省理工学院-IBM沃森人工智能实验室）；Northeastern University（东北大学）
Many model compression techniques of Deep Neural Networks (DNNs) have been investigated, including weight pruning, weight clustering and quantization, etc. Weight pruning leverages the redundancy in the number of weights in DNNs, while weight clustering/quantization leverages the redundancy in the number of bit representations of weights. They can be effectively combined in order to exploit the maximum degree of redundancy. However, there lacks a systematic investigation in literature towards this direction. In this paper, we fill this void and develop a unified, systematic framework of DNN we…
Beijing University of Posts and Telecommunications（北京邮电大学）
Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more attention to designing evaluation criteria of filter importance and then prune less important filters with a fixed pruning rate or a fixed number to reduce convolutional neural networks' redundancy. It does not consider how many filters to reserve for each layer is the most reasonable choice. From this perspective, we propose a new filter pruning method by searc…
FlattenGPT: Depth Compression for Transformer with Layer Flattening
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学）；Tsinghua University（清华大学）
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition. In this paper, we propose a cascade pruning framework named CP-ViT by predicting sparsity in ViT models progressively and dynamically to reduce computational redundancy while minimizing the accuracy loss. Specifically, we define the cumulative score to reserve the informative patches…
University of Electronic Science and Technology of China（电子科技大学）
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make th…
George Mason University（乔治梅森大学）；Clarkson University（克拉克森大学）
Based on filter magnitude ranking (e.g. L1 norm), conventional filter pruning methods for Convolutional Neural Networks (CNNs) have been proved with great effectiveness in computation load reduction. Although effective, these methods are rarely analyzed in a perspective of filter functionality. In this work, we explore the filter pruning and the retraining through qualitative filter functionality interpretation. We find that the filter magnitude based method fails to eliminate the filters with repetitive functionality. And the retraining phase is actually used to reconstruct the remained filte…
ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models
VCIP & TMCC & DISSec, College of Computer Science, Nankai University（VCIP与TMCC与DISSec学院，南开大学计算机科学学院）；LIX, Ecole Polytechnique, IP Paris（LIX，巴黎高等理工学院，IP巴黎）；OPPO Research Institute（OPPO研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy in the number of weights and can be performed in a non-structured, which has higher flexibility and pruning rate but incurs index accesses due to irregular weights, or structured manner, which preserves the full matrix structure with lower pruning rate. Weight quantization leverag…
The redundancy is widely recognized in Convolutional Neural Networks (CNNs), which enables to remove unimportant filters from convolutional layers so as to slim the network with acceptable performance drop. Inspired by the linear and combinational properties of convolution, we seek to make some filters increasingly close and eventually identical for network slimming. To this end, we propose Centripetal SGD (C-SGD), a novel optimization method, which can train several filters to collapse into a single point in the parameter hyperspace. When the training is completed, the removal of the identica…
Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning
School of Computer Jiangsu University of Science and Technology（江苏科技大学计算机学院）；School of Computer and Software Nanjing University of Information Science and Technology（南京信息工程大学计算机与软件学院）；Department of Electrical and Computer Engineering University of Nevada Las Vegas（内华达大学拉斯维加斯分校电气与计算机工程系）
LiePrune: Lie Group and Quantum Geometric Dual Representation for One-Shot Structured Pruning of Quantum Neural Networks
School of Computer, Jiangsu University of Science and Technology（江苏科技大学计算机学院）；Department of Electrical and Computer Engineering, University of Nevada, Las Vegas（内华达大学拉斯维加斯分校电子与计算机工程系）
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Xiaohongshu Inc.（小红书公司）；Shanghai Jiao Tong University（上海交通大学）
TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios
University of Texas Southwestern Medical Center（德克萨斯大学西南医学中心）
OPPO US Research Center InnoPeak Technology（OPPO 美国研究中心 InnoPeak Technology）
For many years, the family of convolutional neural networks (CNNs) has been a workhorse in deep learning. Recently, many novel CNN structures have been designed to address increasingly challenging tasks. To make them work efficiently on edge devices, researchers have proposed various structured network pruning strategies to reduce their memory and computational cost. However, most of them only focus on reducing the number of filter channels per layer without considering the redundancy within individual filter channels. In this work, we explore pruning from another dimension, the kernel size. W…
The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the recent popular network pruning is an effective method to reduce the redundancy of the models. However, the ranking of filters according to their "importance" on different pruning criteria may be inconsistent. One filter could be important according to a certain criterion, while it is unnecessary according to another one, which indicates that each criterion is…
South China University of Technology（华南理工大学）；Monash University（莫纳什大学）
Model compression aims to reduce the redundancy of deep networks to obtain compact models. Recently, channel pruning has become one of the predominant compression methods to deploy deep models on resource-constrained devices. Most channel pruning methods often use a fixed compression rate for all the layers of the model, which, however, may not be optimal. To address this issue, given a target compression rate for the whole model, one can search for the optimal compression rate for each layer. Nevertheless, these methods perform channel pruning for a specific target compression rate. When we c…
