Collaborative Multi-Mode Pruning for Vision-Language Models

• URL: http://arxiv.org/abs/2604.02956v1
• Date: Fri, 03 Apr 2026 10:44:23 GMT
• Title: Collaborative Multi-Mode Pruning for Vision-Language Models
• Abstract summary: Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging.<n>We propose Collaborative Multi-Mode Pruning (CoMP), a novel framework tailored for VLMs by performing joint parameter and token pruning.<n>Our method effectively promotes the performance under high pruning ratios by comparing to the state-of-the-art approaches.
• Score: 31.988586741092927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an effective technique for compressing VLMs, existing approaches predominantly focus on a single mode by pruning either parameters or tokens, neglecting fully exploring the inherent redundancy in each mode, which leads to substantial performance degradation at high pruning ratios. To address the above limitations, we propose Collaborative Multi-Mode Pruning (CoMP), a novel framework tailored for VLMs by performing joint parameter and token pruning. Specifically, we first design a Collaborative Importance Metric (CIM) that investigates the mutual interference between the coupled parameters and tokens. It incorporates distinct significance of tokens into the computation of parameter importance scores, while simultaneously mitigating the affect of pruned parameters on token importance scores. Moreover, we develop a Multi-Mode Pruning Strategy (MPS) that decomposes the overall pruning process into a sequence of pruning stages, while in each stage we estimate the priory of different pruning modes based on their pruning cost and adaptively shift to the optimal one. Additionally, MPS integrates the historical cost and random exploration, in order to achieve a stable pruning process and avoid local optimum. Extensive experiments across various vision-language tasks and models demonstrate that our method effectively promotes the performance under high pruning ratios by comparing to the state-of-the-art approaches. The source code is available at https://github.com/Wuzimeng/CoMP.git.

Related papers

• VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models [74.05545957865228]
  Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs)<n>We introduce, a novel framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations.<n>Our approach employs continuous relaxation and straight-through estimators to enable gradient-based search, solved via the Augmented Lagrangian method.
  arXiv  Detail & Related papers  (2026-04-16T16:21:05Z)
• HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers [3.644142828550762]
  Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on edge devices.<n>We propose Hierarchical Auto-Pruning (HiAP), a continuous relaxation framework that discovers optimal sub-networks in a single end-to-end training phase.<n>HiAP addresses both the memory-bound overhead of loading large matrices and the compute-bound mathematical operations.
  arXiv  Detail & Related papers  (2026-03-12T17:45:38Z)
• MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation [12.481603155570037]
  We propose textbfMMLoP (textbfMulti-textbfModal textbfLow-Rank textbfPrompting), a framework that achieves deep multi-modal prompting with only textbf11.5K trainable parameters.
  arXiv  Detail & Related papers  (2026-02-24T22:00:34Z)
• Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework [39.59931739606983]
  Visual Document Retrieval (VDR) aims to retrieve relevant pages within vast corpora of visually-rich documents.<n>Current efficiency methods like pruning and merging address imperfectly, creating a difficult trade-off between compression rate and feature fidelity.<n>We introduce Prune-then-Merge, a novel two-stage framework that synergizes these complementary approaches.
  arXiv  Detail & Related papers  (2026-02-23T06:45:19Z)
• IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs [11.254129271889035]
  Visual token pruning has emerged as a critical technique for accelerating MLLM inference.<n>IDPruner achieves state-of-the-art performance and superior generalization across diverse architectures and tasks.
  arXiv  Detail & Related papers  (2026-02-10T11:20:24Z)
• Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model [74.99242687133408]
  Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation.<n>We introduce Co-GRPO, which reformulates MDM generation as a unified Markov Decision Process (MDP) that jointly incorporates both the model and the inference schedule.
  arXiv  Detail & Related papers  (2025-12-25T12:06:04Z)
• Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity Scores [2.474203056060563]
  Database Management Systems (DBMSs) are fundamental for managing large-scale and heterogeneous data, and their performance is critically influenced by configuration parameters.<n>Recent research has focused on automated configuration optimization using machine learning; however, existing approaches still exhibit several key limitations.<n>We propose RelTune, a novel framework that represents parameter dependencies as a Graph and learns GNN-based latent embeddings that encode performancerelevant semantics.
  arXiv  Detail & Related papers  (2025-10-31T03:46:42Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer [66.71930982549028]
  Vision-Language Transformers (VLTs) have shown great success recently, but are accompanied by heavy computation costs. We propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs.
  arXiv  Detail & Related papers  (2024-03-05T14:13:50Z)
• Parameter-efficient Tuning of Large-scale Multimodal Foundation Model [68.24510810095802]
  We propose A graceful prompt framework for cross-modal transfer (Aurora) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0.1M trainable parameters to implement the multimodal prompt tuning. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach.
  arXiv  Detail & Related papers  (2023-05-15T06:40:56Z)
• Pruning Self-attentions into Convolutional Layers in Single Path [89.55361659622305]
  Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. We propose Single-Path Vision Transformer pruning (SPViT) to efficiently and automatically compress the pre-trained ViTs. Our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.
  arXiv  Detail & Related papers  (2021-11-23T11:35:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.