EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916770516828160 |
|---|---|
| author | Wang, Zekun Ma, Minghua Wang, Zexin Mu, Rongchuan Shan, Liping Liu, Ming Qin, Bing |
| author_facet | Wang, Zekun Ma, Minghua Wang, Zexin Mu, Rongchuan Shan, Liping Liu, Ming Qin, Bing |
| contents | Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive evaluation across diverse backbones, benchmarks, and metrics. In this work, we systematically evaluate mainstream acceleration techniques for LVLMs, categorized into token and parameter compression. We introduce EffiVLM-Bench, a unified framework for assessing not only absolute performance but also generalization and loyalty, while exploring Pareto-optimal trade-offs. Our extensive experiments and in-depth analyses offer insights into optimal strategies for accelerating LVLMs. We open-source code and recipes for EffiVLM-Bench to foster future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models Wang, Zekun Ma, Minghua Wang, Zexin Mu, Rongchuan Shan, Liping Liu, Ming Qin, Bing Computation and Language Computer Vision and Pattern Recognition Machine Learning Large Vision-Language Models (LVLMs) have achieved remarkable success, yet their significant computational demands hinder practical deployment. While efforts to improve LVLM efficiency are growing, existing methods lack comprehensive evaluation across diverse backbones, benchmarks, and metrics. In this work, we systematically evaluate mainstream acceleration techniques for LVLMs, categorized into token and parameter compression. We introduce EffiVLM-Bench, a unified framework for assessing not only absolute performance but also generalization and loyalty, while exploring Pareto-optimal trade-offs. Our extensive experiments and in-depth analyses offer insights into optimal strategies for accelerating LVLMs. We open-source code and recipes for EffiVLM-Bench to foster future research. |
| title | EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models |
| topic | Computation and Language Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.00479 |