PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

• URL: http://arxiv.org/abs/2604.00886v1
• Date: Wed, 01 Apr 2026 13:33:27 GMT
• Title: PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
• Abstract summary: PixelPrune exploits pixel-level redundancy through predictive-coding-based compression.<n>It supports pixel-lossless compression as well as controlled lossy compression.<n>Experiments show that PixelPrune maintains competitive task accuracy while delivering up to 4.2$times$ inference speedup.
• Score: 10.881130305325767
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution inputs that produce tens of thousands of visual tokens. We observe that this cost is largely wasteful -- across document and GUI benchmarks, only 22--71\% of image patches are pixel-unique, the rest being exact duplicates of another patch in the same image. We propose \textbf{PixelPrune}, which exploits this pixel-level redundancy through predictive-coding-based compression, pruning redundant patches \emph{before} the Vision Transformer (ViT) encoder. Because it operates in pixel space prior to any neural computation, PixelPrune accelerates both the ViT encoder and the downstream LLM, covering the full inference pipeline. The method is training-free, requires no learnable parameters, and supports pixel-lossless compression ($τ{=}0$) as well as controlled lossy compression ($τ{>}0$). Experiments across three model scales and document and GUI benchmarks show that PixelPrune maintains competitive task accuracy while delivering up to 4.2$\times$ inference speedup and 1.9$\times$ training acceleration. Code is available at https://github.com/OPPO-Mente-Lab/PixelPrune.

Related papers

• UIPress: Bringing Optical Token Compression to UI-to-Code Generation [2.462537008029033]
  We propose a lightweight learned compression module for UI-to-Code generation.<n> UIPress combines depthwise-separable convolutions, element-guided spatial reweighting, and Transformer refinement to compress visual tokens to a fixed budget of 256.<n>To the best of our knowledge, UIPress is the first encoder-side learned compression method for the UI-to-Code task.
  arXiv  Detail & Related papers  (2026-04-10T15:58:31Z)
• Representation Alignment for Just Image Transformers is not Easier than You Think [25.669017380539064]
  Representation Alignment (REPA) has emerged as a simple way to accelerate Diffusion Transformers training in latent space.<n>This paper shows that the REPA can fail for Just image Transformers (JiT)<n>We propose PixelREPA, which transforms the alignment target and constrains alignment with a Masked Transformer Adapter.
  arXiv  Detail & Related papers  (2026-03-15T13:08:31Z)
• ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization [59.481950697968706]
  We propose Progressive Generative Image Compression (ProGIC), a compact built on residual vector quantization (RVQ)<n>In RVQ, a sequence of vector quantizers encodes the residuals stage by stage, each with its own codebook.<n>We pair this with a lightweight backbone based on depthwise-separable convolutions and small attention blocks, enabling practical deployment on both GPU and CPU-only devices.
  arXiv  Detail & Related papers  (2026-03-03T11:47:05Z)
• PIO-FVLM: Rethinking Training-Free Visual Token Reduction for VLM Acceleration from an Inference-Objective Perspective [59.24570811503256]
  We propose PIO-FVLM to reduce redundant visual tokens in vision-models (VLMs) to accelerate inference.<n>The proposed PIO-FVLM is training-free and compatible with FlashAttention, friendly to practical application and deployment.<n>On LLaVA-Next-7B, PIO-FVLM retains just 11.1% of visual tokens but maintains 97.2% of the original performance.
  arXiv  Detail & Related papers  (2026-02-04T15:33:10Z)
• PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model [59.32370587806426]
  Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies.<n>We introduce PixelVLA, the first VLA model designed to support both pixel-level reasoning and multimodal prompting with text and visual inputs.<n>Our approach is built on a new visuomotor instruction tuning framework that integrates a multiscale pixel-aware encoder with a visual prompting encoder.
  arXiv  Detail & Related papers  (2025-11-03T13:39:37Z)
• PixNerd: Pixel Neural Field Diffusion [30.872185815524286]
  We propose to model the patch-wise decoding with neural field and present a single-scale, single-stage, efficient, end-to-end solution.<n>Thanks to the efficient neural field representation in PixNerd, we directly achieved 2.15 FID on ImageNet $256times256$ and 2.84 FID on ImageNet $512times512$ without any complex cascade pipeline or VAE.
  arXiv  Detail & Related papers  (2025-07-31T06:07:20Z)
• Transformer based Pluralistic Image Completion with Reduced Information Loss [72.92754600354199]
  Transformer based methods have achieved great success in image inpainting recently. They regard each pixel as a token, thus suffering from an information loss issue. We propose a new transformer based framework called "PUT"
  arXiv  Detail & Related papers  (2024-03-31T01:20:16Z)
• Reduce Information Loss in Transformers for Pluralistic Image Inpainting [112.50657646357494]
  We propose a new transformer based framework "PUT" to keep input information as much as possible. PUT greatly outperforms state-of-the-art methods on image fidelity, especially for large masked regions and complex large-scale datasets.
  arXiv  Detail & Related papers  (2022-05-10T17:59:58Z)
• PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation [88.55256389703082]
  Pixel is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation. In this paper, we propose a progressive pixel synthesis network towards efficient image generation, as Pixel. With much less expenditure, Pixel obtains new state-of-the-art (SOTA) performance on two benchmark datasets.
  arXiv  Detail & Related papers  (2022-04-02T10:55:11Z)

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.