Research map / Vision-language and multimodal / Cross-modal learning
Encode Geometric Diagram as Geo-Graph in Geometry Problem Solving
Wenjun Wu, Lingling Zhang, Bo Zhao, Bo Li, Xinyu Zhang, Yaqiang Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| encode diagram as geo-graph with graph transformer instead of CNN diagram features | PGPSNet · Geometry3K* | Completion accuracy: 65.0 -> 70.6 | Improved |
| encode diagram as geo-graph instead of CNN diagram features | PGPSNet · Geometry3K* | Choice accuracy: 77.9 -> 85.1 | Improved |
| encode diagram as geo-graph instead of CNN diagram features | PGPSNet · PGPS9K | Completion accuracy: 62.7 -> 66.6 | Improved |
| encode diagram as geo-graph instead of CNN diagram features | PGPSNet · PGPS9K | Choice accuracy: 70.4 -> 77.5 | Improved |
| encode diagram as geo-graph | PGPSNet · Geometry3K* | Solution Accuracy: 64.4 -> 69.8 | Improved |
| encode diagram as geo-graph | PGPSNet · PGPS9K | Solution Accuracy: 61.0 -> 64.5 | Improved |
| G3PS versus LANS on Geometry3K* Completion | G3PS · Geometry3K* | Completion accuracy: 71.3 -> 70.6 | No clear effect |
| G3PS versus LANS on PGPS9K Choice | G3PS · PGPS9K | Choice accuracy: 73.8 -> 77.5 | Improved |
| add pre-training, augmentation and spatial, connecting and target attentions together (ablation) | G3PS · Geometry3K* | Completion accuracy: 64.2 -> 70.6 | Improved |
| add pre-training, augmentation and attentions together (ablation) | G3PS · Geometry3K* | Solution Accuracy: 63.3 -> 69.8 | Improved |
Closest papers by meaning
- GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training (ICLR 2025 · similarity 0.91)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.88)
- Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning (CVPR 2026 · similarity 0.87)
- GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation (ICLR 2026 · similarity 0.87)
- Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code (ICML 2026 · similarity 0.86)
- Do Large Language Models Truly Understand Geometric Structures? (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
