EUVIMEDEUVIMED entdecken
Crossref

TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks

Xuanle Zhao, Shuxin Zeng, Xinyuan Cai, Xiang Cheng, Duzhen Zhang, Xiuyi Chen, Bo Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1596-1604

DOI: 10.1609/aaai.v40i2.37136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xuanle Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While Vision Language Models (VLMs) have demonstrated remarkable capabilities in general visual understanding, their application in the chemical domain has been limited, with previous works predominantly focusing on text and thus overlooking critical visual information, such as molecular structures. Current approaches that directly adopt standard VLMs for chemical tasks suffer from two primary issues: (i) computational inefficiency of processing entire chemical images with non-informative backgrounds. (ii) a narrow scope on molecular-level tasks that restricts progress in chemical reasoning. In this work, we propose TinyChemVL, an efficient and powerful chemical VLM that leverages visual token reduction and reaction-level tasks to improve model efficiency and reasoning capacity. Also, we propose ChemRxn-V, a reaction-level benchmark for assessing vision-based reaction recognition and prediction tasks. Directly predicting reaction products from molecular images poses a non-trivial challenge, as it requires models to integrate both recognition and reasoning capacities. Our results demonstrate that, with only 4B parameters, TinyChemVL achieves superior performance on both molecular and reaction tasks, while also demonstrating faster inference and training speeds compared to existing models. Notably, TinyChemVL outperforms ChemVLM while utilizing only 1/16th of the visual tokens. This work builds efficient yet powerful VLMs for chemical domains by co-designing model architecture and task complexity.

Zitieren

APA

Zhao, X., Zeng, S., Cai, X., Cheng, X., Zhang, D., Chen, X., & Xu, B. (2026). TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1596-1604. https://doi.org/10.1609/aaai.v40i2.37136

Vancouver

Zhao X, Zeng S, Cai X, Cheng X, Zhang D, Chen X, et al. TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1596-1604. doi:10.1609/aaai.v40i2.37136

BibTeX
@article{Zhao2026,
  author = {Zhao, Xuanle and Zeng, Shuxin and Cai, Xinyuan and Cheng, Xiang and Zhang, Duzhen and Chen, Xiuyi and Xu, Bo},
  title = {TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {2},
  pages = {1596--1604},
  doi = {10.1609/aaai.v40i2.37136}
}
Kostenlos starten →