Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference

• URL: http://arxiv.org/abs/2512.20839v1
• Date: Tue, 23 Dec 2025 23:30:56 GMT
• Title: Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference
• Authors: Putu Indah Githa Cahyani, Komang David Dananjaya Suartana, Novanto Yudistira,
• Abstract summary: We propose an adaptive visual preprocessing method that adjusts input resolution and spatial coverage based on image content characteristics.<n>The proposed approach combines content-aware image analysis, adaptive resolution selection, and content-aware cropping to reduce visual redundancy prior to vision encoding.<n> Experimental results show that adaptive preprocessing reduces per-image inference time by over 50%, mean full generation time, and achieves a consistent reduction of more than 55% in visual token count.
• Score: 2.8292841621378844
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution visual inputs. While recent architectures such as FastVLM improve efficiency through optimized vision encoders, existing pipelines still rely on static visual preprocessing, leading to redundant computation for visually simple inputs. In this work, we propose an adaptive visual preprocessing method that dynamically adjusts input resolution and spatial coverage based on image content characteristics. The proposed approach combines content-aware image analysis, adaptive resolution selection, and content-aware cropping to reduce visual redundancy prior to vision encoding. Importantly, the method is integrated with FastVLM without modifying its architecture or requiring retraining. We evaluate the proposed method on a subset of the DocVQA dataset in an inference-only setting, focusing on efficiency-oriented metrics. Experimental results show that adaptive preprocessing reduces per-image inference time by over 50\%, lowers mean full generation time, and achieves a consistent reduction of more than 55\% in visual token count compared to the baseline pipeline. These findings demonstrate that input-aware preprocessing is an effective and lightweight strategy for improving deployment-oriented efficiency of vision-language models. To facilitate reproducibility, our implementation is provided as a fork of the FastVLM repository, incorporating the files for the proposed method, and is available at https://github.com/kmdavidds/mlfastlm.

Related papers

• AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition [21.989922235835067]
  AdaptVision is an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach.<n>We show that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.
  arXiv  Detail & Related papers  (2025-12-03T13:43:30Z)
• TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models [29.878993349922368]
  Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks.<n>We propose Temporal Token Fusion (TTF), a training-free approach that integrates historical and current visual representations to enhance VLA inference quality.
  arXiv  Detail & Related papers  (2025-08-15T12:03:34Z)
• 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)
• End-to-End Vision Tokenizer Tuning [73.3065542220568]
  The vision tokenizer optimized for low-level reconstruction is to downstream tasks requiring varied representations and semantics.<n>The loss of the vision tokenization can be the representation bottleneck for target tasks.<n>We propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks.
  arXiv  Detail & Related papers  (2025-05-15T17:59:39Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement [50.93686436282772]
  We aim to delve into the limits of image enhancers both from visual quality and computational efficiency.<n>By rethinking the task demands, we build an explicit connection, i.e., visual quality and computational efficiency are corresponding to model learning and structure design.<n>Ultimately, this achieves efficient low-light image enhancement using only a single convolutional layer, while maintaining excellent visual quality.
  arXiv  Detail & Related papers  (2025-02-27T08:20:03Z)
• 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)
• Efficient Visual State Space Model for Image Deblurring [99.54894198086852]
  Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration.<n>We propose a simple yet effective visual state space model (EVSSM) for image deblurring.<n>The proposed EVSSM performs favorably against state-of-the-art methods on benchmark datasets and real-world images.
  arXiv  Detail & Related papers  (2024-05-23T09:13:36Z)

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.