EUVIMEDEUVIMED entdecken
Crossref

LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit

Chengtao Lv, Bilang Zhang, Yang Yong, Ruihao Gong, Yushi Huang, Shiqiao Gu, Jiajun Wu, Yumeng Shi, Jinyang Guo, Wenya Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24189-24197

DOI: 10.1609/aaai.v40i29.39598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chengtao Lv und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues, recent works have proposed training-free compression methods. However, existing efforts often suffer from three major limitations: (1) Current approaches do not decompose techniques into comparable modules, hindering fair evaluation across spatial and temporal redundancy. (2) Evaluation confined to simple single-turn tasks, failing to reflect performance in realistic scenarios. (3) Isolated use of individual compression techniques, without exploring their joint potential. To overcome these gaps, we introduce LLMC+, a comprehensive VLM compression benchmark with a versatile, plug-and-play toolkit. LLMC+ supports over 20 algorithms across five representative VLM families and enables systematic study of token-level and model-level compression. Our benchmark reveals that: (1) Spatial and temporal redundancies demand distinct technical strategies. (2) Token reduction methods degrade significantly in multi-turn dialogue and detail-sensitive tasks. (3) Combining token and model compression achieves extreme compression with minimal performance loss. We believe LLMC+ will facilitate fair evaluation and inspire future research in efficient VLM.

Zitieren

APA

Lv, C., Zhang, B., Yong, Y., Gong, R., Huang, Y., Gu, S., Wu, J., Shi, Y., Guo, J., & Wang, W. (2026). LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24189-24197. https://doi.org/10.1609/aaai.v40i29.39598

Vancouver

Lv C, Zhang B, Yong Y, Gong R, Huang Y, Gu S, et al. LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24189-24197. doi:10.1609/aaai.v40i29.39598

BibTeX
@article{Lv2026,
  author = {Lv, Chengtao and Zhang, Bilang and Yong, Yang and Gong, Ruihao and Huang, Yushi and Gu, Shiqiao and Wu, Jiajun and Shi, Yumeng and Guo, Jinyang and Wang, Wenya},
  title = {LLMC+: Benchmarking Vision-Language Model Compression with a plug-and-play Toolkit},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {29},
  pages = {24189--24197},
  doi = {10.1609/aaai.v40i29.39598}
}
Kostenlos starten →