mlsanityData to 7 Oct 2026

Texo: Formula Recognition within 20M Parameters

arXiv 2602.17189 ↗First posted 19 Feb 2026cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 19 Feb 2026.

Builds on

27 of 37 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  4. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  5. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  6. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  7. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  8. 2021OCR-free Document Understanding Transformercited by 400
  9. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 240
  10. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 174
  11. 2025DeepSeek-OCR: Contexts Optical Compressioncited by 174
  12. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
15 more
  1. 2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 88
  2. 2016Image-to-Markup Generation with Coarse-to-Fine Attentioncited by 79
  3. 2024Understanding LLMs: A Comprehensive Overview from Training to Inferencecited by 58
  4. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 54
  5. 2024Fast Vocabulary Transfer for Language Model Compressioncited by 42
  6. 2024UniMERNet: A Universal Network for Real-World Mathematical Expression Recognitioncited by 41
  7. 2024Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matchingcited by 39
  8. 2022When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognitioncited by 35
  9. 2021Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformercited by 34
  10. 2020Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attentioncited by 22
  11. 2021Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learningcited by 20
  12. 2025HunyuanOCR Technical Reportcited by 18
  13. 2021Fine-Tuning Transformers: Vocabulary Transfercited by 14
  14. 2019Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressionscited by 13
  15. 2025PP-FormulaNet: Bridging Accuracy and Efficiency in Advanced Formula Recognitioncited by 6

Built on by

Not cited yet.