mlsanityData to 7 Oct 2026

GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving

arXiv 2602.08524 ↗First posted 9 Feb 2026cs.CVcited by 1

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relationships related to geometric theory. To address this, we propose GeoFocus, a novel framework comprising two core modules. 1) Critical Local Perceptor, which automatically identifies and emphasizes critical local structure (e.g., angles, parallel lines, comparative distances) through thirteen theory-based perception templates, boosting critical local feature coverage by 61% compared to previous methods. 2) VertexLang, a compact topology formal language, encodes global figures through vertex coordinates and connectivity relations. By replacing bulky code-based encodings, VertexLang reduces global perception training time by 20% while improving topology recognition accuracy. When evaluated in Geo3K, GeoQA, and FormalGeo7K, GeoFocus achieves a 4.7% accuracy improvement over leading specialized models and demonstrates superior robustness in MATHVERSE under diverse visual conditions. Project Page -- https://github.com/dle666/GeoFocus

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 46 of its 62 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

46 of 62 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation17 Apr
  2. 2025Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration17 Apr
  3. 2024GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training16 Dec
  4. 2024GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation17 Jun
  5. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model18 Dec

Other references · 41

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2025Gemma 3 Technical Reportcited by 1,686
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  7. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  8. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  9. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  10. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  11. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  12. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
29 more
  1. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  2. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  3. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  4. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  5. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 516
  6. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  7. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 356
  8. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  9. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 281
  10. 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Modelscited by 260
  11. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 224
  12. 2022UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expressioncited by 137
  13. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Modelscited by 133
  14. 2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Enginecited by 111
  15. 2023GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoningcited by 107
  16. 2024MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Modelscited by 69
  17. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Modelscited by 64
  18. 2024From LLM to NMT: Advancing Low-Resource Machine Translation with Claudecited by 57
  19. 2023A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagramcited by 55
  20. 2025MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoningcited by 45
  21. 2023FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solvingcited by 26
  22. 2024Slow Perception: Let's Perceive Geometric Figures Step-by-stepcited by 24
  23. 2023LANS: A Layout-Aware Neural Solver for Plane Geometry Problemcited by 23
  24. 2025Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understandingcited by 23
  25. 2023Chain of Images for Intuitively Reasoningcited by 20
  26. 2021Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solvingcited by 11
  27. 2025GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutionscited by 11
  28. 2021Geometry-Aware Fruit Grasping Estimation for Robotic Harvesting in Orchardscited by 6
  29. 2025GeoSDF: Plane Geometry Diagram Synthesis via Signed Distance Fieldcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning
  2. 2024GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models
  3. 2024Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
  4. 2024GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models
  5. 2025CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding
  6. 2025GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation
  7. 2026GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
  8. 2026GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning