Skip to main navigation Skip to search Skip to main content

EFFIVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models

  • Zekun Wang
  • , Minghua Ma
  • , Zexin Wang
  • , Rongchuan Mu
  • , Liping Shan
  • , Ming Liu*
  • , Bing Qin
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Pengcheng Laboratory

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationLong Papers
EditorsWanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
PublisherAssociation for Computational Linguistics (ACL)
Pages25546-25572
Number of pages27
ISBN (Electronic)9798891762510
DOIs
StatePublished - 2025
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: 27 Jul 20251 Aug 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period27/07/251/08/25

Fingerprint

Dive into the research topics of 'EFFIVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models'. Together they form a unique fingerprint.

Cite this