mlsanityData to 14 Oct 2026

Math2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation

arXiv 2609.22647 ↗First posted 18 Sep 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Visual representations can help lower-primary learners understand Math Word Problems, but generating classroom-usable visuals remains difficult. Existing symbolic systems are controllable but limited in coverage, while end-to-end text-to-image systems often fail to satisfy exact mathematical constraints. This paper presents a symbolic visual generation framework for lower-primary MWP generation with broader problem coverage and more scalable asset generation. The framework includes an LLM-based routing layer, three worksheet-oriented generation modules, and two fallback mechanisms for open-world SVG asset acquisition. A human evaluation comparing Math2Visual-X with Stable Diffusion XL, Nano Banana, and GPT Image showed that the proposed method achieved the strongest overall performance. The results indicate that the framework offers a scalable and pedagogically grounded approach for automatic MWP visual generation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 18 Sep 2026.

Builds on

18 of 32 references.

References · 18

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  7. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  8. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  9. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  10. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  11. 2023ImagenHub: Standardizing the evaluation of conditional image generation modelscited by 77
  12. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 76
6 more
  1. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 66
  2. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Modelscited by 38
  3. 2025Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understandingcited by 24
  4. 2025Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Helpcited by 12
  5. 2024CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Modelscited by 7
  6. 2025Can Vision-Language Models Solve Visual Math Equations?cited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities
  2. 2025DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students' Hand-Drawn Math Images
  3. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
  4. 2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
  5. 2024MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts
  6. 2025CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
  7. 2026Visual Reasoning Benchmark: Evaluating Multimodal LLMs on Classroom-Authentic Visual Problems from Primary Education
  8. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation