Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

• URL: http://arxiv.org/abs/2412.01818v2
• Date: Sun, 11 May 2025 17:45:02 GMT
• Title: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
• Authors: Qizhe Zhang, Aosong Cheng, Ming Lu, Renrui Zhang, Zhiyong Zhuo, Jiajun Cao, Shaobo Guo, Qi She, Shanghang Zhang,
• Abstract summary: Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts.<n>We propose VisPruner, a plug-and-play method that utilizes visual cues for more effective token pruning in LVLMs.<n>Our results show that VisPruner can reduce the FLOPs of LLaVA-1.5-7B by 91% and inference latency by 75%, while maintaining comparable performance.
• Score: 34.3615740255575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent efforts have been made to tackle this issue by pruning visual tokens early within the language model. Most existing works use attention scores between text and visual tokens to assess the importance of visual tokens. However, in this study, we first analyze the text-visual attention in the language model and find that this score is not an ideal indicator for token pruning. Based on the analysis, We propose VisPruner, a plug-and-play method that utilizes visual cues for more effective token pruning in LVLMs. Specifically, we first use visual attention to select a limited number of significant tokens. Then, we remove duplicate tokens from the remaining ones based on their similarity. By retaining diverse tokens alongside the initially selected important tokens, we maximally preserve the visual information of the input image. Experimental results demonstrate that our VisPruner sustains strong performance across various VLM architectures and reduction ratios, significantly outperforming existing methods based on text-visual attention. Notably, without any training, VisPruner can reduce the FLOPs of LLaVA-1.5-7B by 91% and inference latency by 75%, while maintaining comparable performance. Our code is available at https://github.com/Theia-4869/VisPruner.

Related papers

• VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization [49.5501769221435]
  Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information.<n>Previous research aimed at reducing visual tokens during inference typically leverages importance maps derived from attention scores among vision-only tokens or vision-language tokens to prune tokens across one or multiple pruning stages.<n>We propose VFlowOpt, a token pruning framework that introduces an importance map derivation process and a progressive pruning module with a recycling mechanism.<n> Experiments demonstrate that VFlowOpt can prune 90% of visual tokens while maintaining comparable performance, leading to an 89% reduction in KV-Cache memory and 3.8
  arXiv  Detail & Related papers  (2025-08-07T09:47:21Z)
• Rethinking Visual Token Reduction in LVLMs under Cross-modal Misalignment [38.04426918886084]
  Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics.<n>Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs)<n>We introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention.
  arXiv  Detail & Related papers  (2025-06-27T14:55:40Z)
• ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models [59.47738955960352]
  ToDRE is a two-stage and training-free token compression framework.<n>It achieves superior performance by pruning tokens based on token Diversity and token-task RElevance.
  arXiv  Detail & Related papers  (2025-05-24T15:47:49Z)
• Window Token Concatenation for Efficient Visual Large Language Models [59.6094005814282]
  We propose Window Token Concatenation (WiCo) to reduce visual tokens in Visual Large Language Models (VLLMs) WiCo group diverse tokens into one, and thus obscure some fine details. We perform extensive experiments on both coarse- and fine-grained visual understanding tasks based on LLaVA-1.5 and Shikra, showing better performance compared with existing token reduction projectors.
  arXiv  Detail & Related papers  (2025-04-05T02:32:58Z)
• Beyond Intermediate States: Explaining Visual Redundancy through Language [7.275188652473603]
  Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens.<n>Visual tokens with low ViT-[cls] association and low text-to-image attention scores can contain recognizable information.<n>We develop a more reliable method for identifying and pruning redundant visual tokens.
  arXiv  Detail & Related papers  (2025-03-26T13:38:10Z)
• TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model [56.43860351559185]
  We introduce textbfTopV, a compatible textbfTOken textbfPruning with inference Time Optimization for fast and low-memory textbfVLM.<n>Our framework incorporates a visual-aware cost function to measure the importance of each source visual token, enabling effective pruning of low-importance tokens.
  arXiv  Detail & Related papers  (2025-03-24T01:47:26Z)
• Introducing Visual Perception Token into Multimodal Large Language Model [53.82301522384719]
  Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder.<n>MLLM still lacks the autonomous capability to control its own visual perception processes.<n>We propose the concept of Visual Perception Token, aiming to empower MLLM with a mechanism to control its visual perception processes.
  arXiv  Detail & Related papers  (2025-02-24T18:56:12Z)
• What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph [15.364317811275344]
  We propose a graph-based method towards training-free visual token pruning, termed G-Prune.<n>G-Prune regards visual tokens as nodes, and construct their connections based on their semantic similarities.<n>Experiment results show that G-Prune can greatly reduce computation overhead while retaining high performance on both coarse- and fine-grained tasks.
  arXiv  Detail & Related papers  (2025-01-04T12:14:42Z)
• [CLS] Token Tells Everything Needed for Training-free Efficient MLLMs [66.5266435598799]
  Multi-language Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision tasks. However, their efficient deployment remains a substantial challenge due to high computational costs and memory requirements. We introduce a simple yet effective method for train-free visual compression, called VTC- compression.
  arXiv  Detail & Related papers  (2024-12-08T05:29:39Z)
• FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression [76.01465333271229]
  multimodal large language models (MLLMs) behave like a sloth in practical use. Recent efforts are devoted to building tiny MLLMs for better efficiency, but the plethora of visual tokens still used limit their actual speedup. In this paper, we propose a powerful and fast tiny MLLM called FlashSloth.
  arXiv  Detail & Related papers  (2024-12-05T16:34:07Z)
• A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs [65.00970402080351]
  A promising approach to accelerating large vision-language models (VLMs) is using partial information, such as attention maps from specific layers, to assess token importance and prune less essential tokens. Our study reveals three key insights: (i) Partial attention information is insufficient for accurately identifying critical visual tokens, resulting in suboptimal performance, especially at low token retention ratios; (ii) Global attention information, such as the attention map aggregated across all layers, more effectively preserves essential tokens and maintains comparable performance under aggressive pruning; and (iii) The global attention map aggregated from a small VLM closely resembles that of a large VLM,
  arXiv  Detail & Related papers  (2024-12-04T13:56:44Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation.<n>We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE)<n>DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Inference Optimal VLMs Need Only One Visual Token but Larger Models [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. VLMs are often constrained by high latency during inference due to substantial compute required to process the large number of input tokens. We take some initial steps towards building approaches tailored for high token compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)
• Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers [32.167072183575925]
  We propose a method that reduces the number of visual tokens by summarizing them into a smaller set of register tokens. Victor shows less than a 4% accuracy drop while reducing the total training time by 43% and boosting the inference throughput by 3.3X.
  arXiv  Detail & Related papers  (2024-10-17T22:45:13Z)
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference [45.11612407862277]
  In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead. We propose an efficient training-free token optimization mechanism dubbed SparseVLM without extra parameters or fine-tuning costs. Experimental results show that our SparseVLM improves the efficiency of various VLMs across a range of image and video understanding tasks.
  arXiv  Detail & Related papers  (2024-10-06T09:18:04Z)
• Balancing Performance and Efficiency: A Multimodal Large Language Model Pruning Method based Image Text Interaction [6.467840081978855]
  multimodal large language models (MM-LLMs) have achieved great success in many multimodal tasks, but their high computational costs limit their further promotion and application. We studied the visual tokens of MM-LLMs and designed a dynamic pruning algorithm to address this issue. Our proposed method can achieve performance that competes with the original performance when using an average of 22% of the original token quantity.
  arXiv  Detail & Related papers  (2024-09-02T10:49:10Z)
• TokenPacker: Efficient Visual Projector for Multimodal LLM [37.1071749188282]
  The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) We propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. Our approach compresses the visual tokens by 75%89%, while achieves comparable or even better performance across diverse benchmarks.
  arXiv  Detail & Related papers  (2024-07-02T16:10:55Z)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)

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.