Texo: Formula Recognition within 20M Parameters
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910026854039552 |
|---|---|
| author | Mao, Sicheng |
| author_facet | Mao, Sicheng |
| contents | In this paper we present Texo, a minimalist yet highperformance formula recognition model that contains only 20 million parameters. By attentive design, distillation and transfer of the vocabulary and the tokenizer, Texo achieves comparable performance to state-of-the-art models such as UniMERNet-T and PPFormulaNet-S, while reducing the model size by 80% and 65%, respectively. This enables real-time inference on consumer-grade hardware and even in-browser deployment. We also developed a web application to demonstrate the model capabilities and facilitate its usage for end users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17189 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Texo: Formula Recognition within 20M Parameters Mao, Sicheng Artificial Intelligence Computer Vision and Pattern Recognition In this paper we present Texo, a minimalist yet highperformance formula recognition model that contains only 20 million parameters. By attentive design, distillation and transfer of the vocabulary and the tokenizer, Texo achieves comparable performance to state-of-the-art models such as UniMERNet-T and PPFormulaNet-S, while reducing the model size by 80% and 65%, respectively. This enables real-time inference on consumer-grade hardware and even in-browser deployment. We also developed a web application to demonstrate the model capabilities and facilitate its usage for end users. |
| title | Texo: Formula Recognition within 20M Parameters |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.17189 |