AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance

• URL: http://arxiv.org/abs/2508.06084v1
• Date: Fri, 08 Aug 2025 07:27:26 GMT
• Title: AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance
• Authors: Weichen Zhang, Zhui Zhu, Ningbo Li, Kebin Liu, Yunhao Liu,
• Abstract summary: Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering (VQA)<n>Their inference cost remains a significant challenge due to the large number of vision tokens processed during the prefill stage.<n>Existing pruning methods often rely on directly using the attention patterns or static text prompt guidance, failing to exploit the dynamic internal signals generated during inference.<n>We propose AdaptInfer, a plug-and-play framework for adaptive vision token pruning inVLMs.
• Score: 7.594255363909475
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering (VQA), but their inference cost remains a significant challenge due to the large number of vision tokens processed during the prefill stage. Existing pruning methods often rely on directly using the attention patterns or static text prompt guidance, failing to exploit the dynamic internal signals generated during inference. To address these issues, we propose AdaptInfer, a plug-and-play framework for adaptive vision token pruning in VLMs. First, we introduce a fine-grained, dynamic text-guided pruning mechanism that reuses layer-wise text-to-text attention maps to construct soft priors over text-token importance, allowing more informed scoring of vision tokens at each stage. Second, we perform an offline analysis of cross-modal attention shifts and identify consistent inflection locations in inference, which inspire us to propose a more principled and efficient pruning schedule. Our method is lightweight and plug-and-play, also generalizable across multi-modal tasks. Experimental results have verified the effectiveness of the proposed method. For example, it reduces CUDA latency by 61.3\% while maintaining an average accuracy of 92.9\% on vanilla LLaVA-1.5-7B. Under the same token budget, AdaptInfer surpasses SOTA in accuracy.

Related papers

• Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning [82.39668822222386]
  Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM)<n>We propose $textNwa$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity.<n>Experiments demonstrate that $textNwa$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%)
  arXiv  Detail & Related papers  (2026-02-03T00:51:03Z)
• ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models [7.7352936204066]
  We propose a novel, zero-shot method to model visual token pruning as a balance between task relevance and information diversity.<n>Our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss.<n>These gains are accompanied by significant reductions in GPU memory footprint and inference latency.
  arXiv  Detail & Related papers  (2025-10-20T06:18:47Z)
• HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models [23.98782884568504]
  We propose Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models (HiViS)<n>HiViS is an explicit-implicit input decomposition framework that alleviates the inefficiency of Speculative Decoding in Vision-Language Models.<n>Our approach compresses the prefill sequence length of the drafter to only 0.7%-1.3% of the target VLM's input.
  arXiv  Detail & Related papers  (2025-09-28T15:05:21Z)
• A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models [94.49953824684853]
  We introduce a dynamic pruning framework, GlimpsePrune, inspired by human cognition.<n>It takes a data-driven ''glimpse'' and prunes irrelevant visual tokens in a single forward pass before answer generation.<n>An enhanced GlimpsePrune+ achieves 110% of the baseline performance while maintaining a similarly high pruning rate.
  arXiv  Detail & Related papers  (2025-08-03T02:15:43Z)
• 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)
• 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)
• Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models [85.51753014478315]
  We introduce AdaptPrune, a novel plug-and-play training-free pruning method.<n>It builds on conventional attention-based pruning by integrating spatial distance and token similarity with an adaptive NMS approach.<n>Our approach ensures a comprehensive evaluation of token importance and substantially refines the pruning decisions.
  arXiv  Detail & Related papers  (2025-03-11T03:58:17Z)
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model [41.55165760439727]
  Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks.<n>We propose a graph-based approach for label-efficient adaptation and inference.<n>Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning.
  arXiv  Detail & Related papers  (2024-12-24T09:15:00Z)
• 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.<n>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)
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models [10.713680139939354]
  Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks. PETL has garnered attention as a viable alternative to full fine-tuning. We propose a new adapter architecture, $p$-adapter, which employs $p$-Laplacian message passing in Graph Neural Networks (GNNs)
  arXiv  Detail & Related papers  (2023-12-17T05:30:35Z)
• Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection [87.39089806069707]
  We propose a fine-grained Visual-Text Prompt-driven self-training paradigm for Open-Vocabulary Detection (VTP-OVD) During the adapting stage, we enable VLM to obtain fine-grained alignment by using learnable text prompts to resolve an auxiliary dense pixel-wise prediction task. Experiments show that our method achieves the state-of-the-art performance for open-vocabulary object detection, e.g., 31.5% mAP on unseen classes of COCO.
  arXiv  Detail & Related papers  (2022-11-02T03:38:02Z)

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.