Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models

• URL: http://arxiv.org/abs/2603.16001v1
• Date: Mon, 16 Mar 2026 23:23:05 GMT
• Title: Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
• Abstract summary: We propose a simple yet effective Asymmetric Text-Visual Weight Pruning method for Large Vision-Language Models.<n>ATV-Pruning integrates two primary innovations: first, a calibration pool is adaptively constructed by drawing on all textual tokens and a subset of visual tokens.
• Score: 51.475129418355465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process calibration data from different modalities in a unified manner, overlooking modality-specific behaviors. This raises a critical challenge: how to address the divergent behaviors of textual and visual tokens for accurate pruning of LVLMs. To this end, we systematically investigate the sensitivity of visual and textual tokens to the pruning operation by decoupling their corresponding weights, revealing that: (i) the textual pathway should be calibrated via text tokens, since it exhibits higher sensitivity than the visual pathway; (ii) the visual pathway exhibits high redundancy, permitting even 50% sparsity. Motivated by these insights, we propose a simple yet effective Asymmetric Text-Visual Weight Pruning method for LVLMs, dubbed ATV-Pruning, which establishes the importance metric for accurate weight pruning by selecting the informative tokens from both textual and visual pathways. Specifically, ATV-Pruning integrates two primary innovations: first, a calibration pool is adaptively constructed by drawing on all textual tokens and a subset of visual tokens; second, we devise a layer-adaptive selection strategy to yield important visual tokens. Finally, extensive experiments across standard multimodal benchmarks verify the superiority of our ATV-Pruning over state-of-the-art methods.

Related papers

• SignLlama: Enhancing Gloss-free Sign Language Translation by Prioritizing Visual Features for LLMs [24.378058252362646]
  We show that there are two key issues that need to be solved to adapt Large Language Models to the Gloss-Free Sign Language Translation task.<n>First, we propose a simple yet effective method named Filtered Pseudo-Gloss CTC Pretraining.<n>Second, we define a visual-only prediction path in which text inputs are masked, and the model is required to generate the target sequence relying solely on visual inputs.
  arXiv  Detail & Related papers  (2026-08-10T01:47:30Z)
• 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)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models [75.88232735646018]
  Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos.<n>Existing methods attempt to prune redundant vision tokens, revealing substantial redundancy in visual representations.<n>We propose CoViPAL, a layer-wise contextualized visual token pruning method that employs a Plug-and-Play Pruning Module (PPM) to predict and remove redundant vision tokens before they are processed by the LVLM.
  arXiv  Detail & Related papers  (2025-08-24T07:47:00Z)
• AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance [7.594255363909475]
  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.
  arXiv  Detail & Related papers  (2025-08-08T07:27:26Z)
• 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)
• Revisit What You See: Disclose Language Prior in Vision Tokens for LVLM Decoding [6.612630497074871]
  Large Vision-Language Models (LVLMs) achieve strong performance across multimodal tasks by integrating visual perception with language understanding.<n>We propose ReVisiT, a training-free decoding method that references vision tokens to guide text generation.
  arXiv  Detail & Related papers  (2025-06-11T08:46:55Z)
• Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training [78.60953331455565]
  PRIOR is a vision-language pre-training approach that prioritizes image-related tokens through differential weighting in the NTP loss.<n>We observe 19% and 8% average relative improvement, respectively, on several vision-language benchmarks compared to NTP.
  arXiv  Detail & Related papers  (2025-05-13T21:27:52Z)
• D-Attn: Decomposed Attention for Large Vision-and-Language Models [29.611769371733672]
  We propose Decomposed Attention (D-Attn), a more flexible attention architecture for large vision-and-language models (LVLMs)<n>D-Attn decomposes the 1-D causal self-attention of LVLMs into visual-to-visual, textual-to-visual, and textual-to-textual attentions.<n>Experiments and analysis validate the effectiveness of D-Attn, demonstrating significant improvements on multiple image benchmarks.
  arXiv  Detail & Related papers  (2025-02-04T00:46:11Z)
• See then Tell: Enhancing Key Information Extraction with Vision Grounding [32.445618057103324]
  We introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision grounding.<n>To enhance the model's seeing capabilities, we collect extensive structured table recognition datasets.<n>Our approach demonstrates substantial advancements in KIE performance, achieving state-of-the-art results on publicly available datasets.
  arXiv  Detail & Related papers  (2024-09-29T06:21:05Z)
• Instruction Tuning-free Visual Token Complement for Multimodal LLMs [51.138806401996696]
  multimodal large language models (MLLMs) have promised an elegant bridge between vision and language. We propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features. Our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens.
  arXiv  Detail & Related papers  (2024-08-09T12:13:01Z)
• PV2TEA: Patching Visual Modality to Textual-Established Information Extraction [59.76117533540496]
  We patch the visual modality to the textual-established attribute information extractor. PV2TEA is an encoder-decoder architecture equipped with three bias reduction schemes. Empirical results on real-world e-Commerce datasets demonstrate up to 11.74% absolute (20.97% relatively) F1 increase over unimodal baselines.
  arXiv  Detail & Related papers  (2023-06-01T05:39:45Z)
• Visually-augmented pretrained language models for NLP tasks without images [77.74849855049523]
  Existing solutions often rely on explicit images for visual knowledge augmentation. We propose a novel textbfVisually-textbfAugmented fine-tuning approach. Our approach can consistently improve the performance of BERT, RoBERTa, BART, and T5 at different scales.
  arXiv  Detail & Related papers  (2022-12-15T16:13:25Z)

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.