paper-with-me

홈 › Papers

ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models

2025-05-24 · Duo Li, Zuhao Yang, Shijian Lu

The representation of visual inputs of large vision-language models (LVLMs) usually involves substantially more tokens than that of textual inputs, leading to significant computational overhead. Several recent studies strive to mitigate this issue by either conducting token compression to prune redundant visual tokens or guiding them to bypass certain computational stages. While most existing work exploits token importance as the redundancy indicator, our study reveals that two largely neglected factors, namely, the diversity of retained visual tokens and their task relevance, often offer more robust criteria in token pruning. To this end, we design ToDRE, a two-stage and training-free token compression framework that achieves superior performance by pruning Tokens based on token Diversity and token-task RElevance. Instead of pruning redundant tokens, ToDRE introduces a greedy k-center algorithm to select and retain a small subset of diverse visual tokens after the vision encoder. Additionally, ToDRE addresses the "information migration" by further eliminating task-irrelevant visual tokens within the decoder of large language model (LLM). Extensive experiments show that ToDRE effectively reduces 90% of visual tokens after vision encoder and adaptively prunes all visual tokens within certain LLM's decoder layers, leading to a 2.6x speed-up in total inference time while maintaining 95.1% of model performance and excellent compatibility with efficient attention operators.

📄 PDF Abstract BibTeX arXiv:2505.18757

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDiversityLarge Language Model

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Pruning 설명 없음

Similar Papers 제목 키워드 기반

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models

2025-10-20 · Pu Zhang, Yuwei Li, Xingyuan Xian, Guoming Tang arxiv

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. Whi…

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts

2025-12-28 · Hao Zhang, Mengsi Lyu, Bo Huang, Yulong Ao 외 arxiv

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by…

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

2026-06-25 · Tinghao Wang, Yichen Guo, Rui Huang, Zheng Lu 외 arxiv

Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. …

Multimodal Reasoning

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models

2025-06-16 · Ruiguang Pei, Weiqing Sun, Zhihui Fu, Jun Wang

Although Large Vision Language Models (LVLMs) have demonstrated remarkable performance in image understanding tasks, their computational efficiency remains a significant challenge, particularly on resource-constrained de…

Combinatorial OptimizationComputational EfficiencyDiversity

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

2026-06-02 · Jiahui Wang, Kai Zhang, Mai Han, Huanghe Zhang arxiv

Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predom…