TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
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_ | 1866917106268766208 |
|---|---|
| author | Zhao, Xuanle Zeng, Shuxin Cai, Xinyuan Cheng, Xiang Zhang, Duzhen Chen, Xiuyi Xu, Bo |
| author_facet | Zhao, Xuanle Zeng, Shuxin Cai, Xinyuan Cheng, Xiang Zhang, Duzhen Chen, Xiuyi Xu, Bo |
| contents | 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 \textbf{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 \textbf{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 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06283 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks Zhao, Xuanle Zeng, Shuxin Cai, Xinyuan Cheng, Xiang Zhang, Duzhen Chen, Xiuyi Xu, Bo Computer Vision and Pattern Recognition 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 \textbf{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 \textbf{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 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. |
| title | TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.06283 |