LFTR: Learning-Free Token Reduction for Multimodal Large Language Models

• URL: http://arxiv.org/abs/2501.17391v3
• Date: Tue, 30 Sep 2025 10:14:30 GMT
• Title: LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
• Authors: Zihui Zhao, Yingxin Li, Yang Li,
• Abstract summary: We introduce a learning-free token reduction (LFTR) method designed for Multimodal Large Language Models (MLLMs)<n>By capitalizing on the redundancy in visual representations, our approach effectively reduces tokens while preserving the general inference performance of MLLMs.<n>Our results show that LFTR achieves up to a $16times$ reduction of visual tokens while maintaining or even enhancing performance on mainstream vision question-answering benchmarks.
• Score: 3.368594680297987
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional success in various multimodal tasks, yet their deployment is frequently limited by substantial computational demands and prolonged inference times. Given that the vision modality typically contains more comprehensive information than the text modality, resulting in encoded representations comprising an extensive number of tokens, leading to significant computational overhead due to the quadratic complexity of the attention mechanism. Current token reduction methods are typically restricted to specific model architectures and often necessitate extensive retraining or fine-tuning, restricting their applicability to many state-of-the-art models. In this paper, we introduce a learning-free token reduction (LFTR) method designed for MLLMs. LFTR can be seamlessly integrated into most open-source MLLM architectures without requiring additional fine-tuning. By capitalizing on the redundancy in visual representations, our approach effectively reduces tokens while preserving the general inference performance of MLLMs. We conduct experiments on multiple MLLM architectures (LLaVA, MiniGPT, QwenVL), and our results show that LFTR achieves up to a $16\times$ reduction of visual tokens while maintaining or even enhancing performance on mainstream vision question-answering benchmarks, all in a learning-free setting. Additionally, LFTR is complementary to other acceleration techniques, such as vision encoder compression and post-training quantization, further promoting the efficient deployment of MLLMs. Our project is available at https://anonymous.4open.science/r/LFTR-AAAI-0528.

Related papers

• Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs [10.443777669301983]
  Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval.<n>But their practical application is often hindered by the substantial computational cost incurred from processing a large number of tokens from visual inputs.<n>We propose Magic-MM-Embedding, a series of novel models that achieve both high efficiency and state-of-the-art performance in universal multimodal embedding.
  arXiv  Detail & Related papers  (2026-02-05T04:01:01Z)
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models [85.30893355216486]
  We study how visual token redundancy evolves with different dMLLM architectures and tasks.<n>Our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks.<n>Layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs.
  arXiv  Detail & Related papers  (2025-11-19T04:13:36Z)
• Language Models Coupled with Metacognition Can Outperform Reasoning Models [32.32646975975768]
  Large language models (LLMs) excel in speed and adaptability across various reasoning tasks.<n>LRMs are specifically designed for complex, step-by-step reasoning.<n> SOFAI-LM coordinates a fast LLM with a slower but more powerful LRM through metacognition.
  arXiv  Detail & Related papers  (2025-08-25T12:19:57Z)
• ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models [67.75439511654078]
  Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses.<n>They face the persistent challenge of hallucination, which introduces practical weaknesses and raises concerns about their reliable deployment in real-world applications.<n>We propose ONLY, a training-free decoding approach that requires only a single query and a one-layer intervention during decoding, enabling efficient real-time deployment.
  arXiv  Detail & Related papers  (2025-07-01T16:01:08Z)
• GenRecal: Generation after Recalibration from Large to Small Vision-Language Models [63.27511432647797]
  Vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V.<n>Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V.
  arXiv  Detail & Related papers  (2025-06-18T17:59:49Z)
• GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models [5.025353943896242]
  GreedyPrune is a training-free visual token pruning algorithm designed to optimize semantic saliency and visual diversity.<n>We show that GreedyPrune achieves state-of-the-art accuracy across various multimodal tasks and models while significantly reducing end-to-end inference latency.
  arXiv  Detail & Related papers  (2025-06-16T07:21:11Z)
• LeMoRe: Learn More Details for Lightweight Semantic Segmentation [48.81126061219231]
  We introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity.<n>Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies.
  arXiv  Detail & Related papers  (2025-05-29T04:55:10Z)
• Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning [70.57180215148125]
  Visual instruction tuning aims to enable large language models to comprehend the visual world.<n>Existing methods often grapple with the intractable trade-off between accuracy and efficiency.<n>We present LLaVA-Meteor, a novel approach that strategically compresses visual tokens without compromising core information.
  arXiv  Detail & Related papers  (2025-05-17T10:22:29Z)
• Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model [63.14883657299359]
  Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering.<n> tuning MLLMs for downstream tasks encounters two key challenges: Task-Expert, where distribution shifts between pre-training and target datasets constrain target performance, and OpenWorld Stabilization, where catastrophic forgetting erases the model general knowledge.
  arXiv  Detail & Related papers  (2025-03-06T15:29:13Z)
• FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance [7.889590793589825]
  We introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence.<n>We analyze the information loss introduced by different reduction strategies and develop FOLDER to preserve key information while removing visual redundancy.<n>FOLDER achieves comparable or even better performance than the original models, while dramatically reducing complexity by removing up to 70% of visual tokens.
  arXiv  Detail & Related papers  (2025-01-05T03:28:45Z)
• SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding [66.74446220401296]
  We propose SynerGen-VL, a simple yet powerful encoder-free MLLM capable of both image understanding and generation.<n>We introduce the token folding mechanism and the vision-expert-based progressive alignment pretraining strategy, which effectively support high-resolution image understanding.<n>Our code and models shall be released.
  arXiv  Detail & Related papers  (2024-12-12T18:59:26Z)
• AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning [19.68349294206012]
  Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos.<n>We propose a training-free adaptive inference method for multi-modal LLMs that can accommodate a broad range of efficiency requirements.
  arXiv  Detail & Related papers  (2024-12-04T11:47:57Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [66.04061083611863]
  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)
• Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
  High-resolution images and videos pose a barrier to their broader adoption.<n> compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.<n>We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
  arXiv  Detail & Related papers  (2024-11-26T09:36:02Z)
• FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression [45.37530855889661]
  High-resolution images lead to a quadratic increase in the number of visual tokens input into Multi-modal Large Language Models. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.
  arXiv  Detail & Related papers  (2024-11-21T15:37:52Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [72.68665884790002]
  We propose a novel framework to transfer knowledge from l-MLLMs to s-MLLMs.<n>We introduce Multimodal Distillation (MDist) to transfer teacher model's robust representations across both visual and linguistic modalities.<n>We also propose a three-stage training scheme to fully exploit the potential of the proposed distillation strategy.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering [53.39158264785098]
  Long-term Video Question Answering (VideoQA) is a challenging vision-and-language bridging task. We present an entirely end-to-end solution for VideoQA: Multi-granularity Contrastive cross-modal collaborative Generation model.
  arXiv  Detail & Related papers  (2024-10-12T06:21:58Z)
• M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning [90.75075886543404]
  Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains. In this work, we introduce a novel Multimodal Prompt Tuning (M$2$PT) approach for efficient instruction tuning of MLLMs.
  arXiv  Detail & Related papers  (2024-09-24T01:40:24Z)
• Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs [14.533229831531168]
  We introduce a new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.<n>Inspired by human attention patterns in Visual Question Answering (VQA) tasks, TRIM presents a fresh perspective on the selection and reduction of image tokens.<n>The results demonstrate a significant reduction in computational overhead while maintaining a consistent level of performance.
  arXiv  Detail & Related papers  (2024-09-17T08:56:27Z)
• Robust Latent Representation Tuning for Image-text Classification [9.789498730131607]
  We propose a robust latent representation tuning method for large models. Our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation. Within this framework, common semantics are refined during training, and robust performance is achieved even in the absence of one modality.
  arXiv  Detail & Related papers  (2024-06-10T06:29:00Z)
• NoteLLM-2: Multimodal Large Representation Models for Recommendation [71.87790090964734]
  Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks.<n>Their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored.<n>We propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision encoders for efficient multimodal representation.
  arXiv  Detail & Related papers  (2024-05-27T03:24:01Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)

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.