AICVFeb 19

Texo: Formula Recognition within 20M Parameters

arXiv:2602.17189v1
Originality Incremental advance
AI Analysis

This work addresses efficient formula recognition for end users, enabling deployment on consumer-grade hardware, but it is incremental as it builds on existing methods with size reduction.

The paper tackles formula recognition by introducing Texo, a minimalist model with only 20 million parameters that achieves comparable performance to state-of-the-art models while reducing size by 80% and 65%, enabling real-time inference on consumer hardware.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes