paper-with-me

홈 › Papers

Object-Centric Vision Token Pruning for Vision Language Models

2025-11-25 · Guangyuan Li, Rongzhen Zhao, Jinhong Deng, Yanbo Wang, Joni Pajarinen arxiv

In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too much unnecessary computation. Pruning redundant vision tokens for high VLM inference efficiency has been continuously studied but all existing methods resort to indirect and non-guaranteed ways. We propose OC-VTP, a direct and guaranteed approach to select the most representative vision tokens for high-efficiency yet accuracy-preserving VLM inference. Our OC-VTP requires merely light-weight pre-training of a small object-centric vision token pruner, which can then be inserted into existing VLMs, without fine-tuning of any models on any datasets. It is gauranteed that the most representative vision tokens are kept by minimizing the error in reconstructing the original unpruned tokens from the selected ones. Across any vision pruning ratios, i.e., inference efficiency, our OC-VTP consistently helps mainstream VLMs to preserve the highest inference accuracy. Our pruning also demonstrates interesting interpretability. Our codes are available at https://github.com/GarryLarry010131/OC-VTP.

📄 PDF Abstract BibTeX arXiv:2511.20439

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning

2025-03-31 · Bizhe Bai, JianJian Cao, Yadan Luo, Tao Chen

Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding object segmentation masks. Recent models, s…

Semantic SegmentationToken Reduction

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

2024-12-17 · Mark Endo, Xiaohan Wang, Serena Yeung-Levy

Recent works on accelerating Vision-Language Models show that strong performance can be maintained across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the pop…

Language ModelingLanguage Modelling

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models

2025-09-28 · Rokas Bendikas, Daniel Dijkman, Markus Peschl, Sanjay Haresh 외 arxiv

Vision-Language-Action (VLA) models offer a pivotal approach to learning robotic manipulation at scale by repurposing large pre-trained Vision-Language-Models (VLM) to output robotic actions. However, adapting VLMs for r…

Representation Learning

Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance

2025-04-02 · Taehan Lee, Hyukjun Lee

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by se…

Audio Classification

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models

2025-08-01 · Jizhihui Liu, Feiyi Du, Guangdao Zhu, Niu Lian 외 arxiv

Vision-Language Models (VLMs) encode images and videos into abundant tokens, which contain substantial redundancy and computation cost. While visual token pruning mitigates the issue, most existing methods lack insight i…

Instruction Following