GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions
Jo-Ku Cheng, Zeren Zhang, Ran Chen, Jingyang Deng, Ziran Qin, Jinwen Ma
Abstract
<formalization> consCDL: Shape(BO,OE,EB), Shape(BE,EA,AB), Shape(OAB,BA), Shape(ED,DA,AE),Shape(ODA,AD),Shape(CO,OB,BC), Shape(OBC,CB), Shape(OCD,DE,EO,OC), Collinear(OEA), Collinear(BED), Cocircular(O,ABCD) imgCDL: Equal(LengthOfLine(AB), LengthOfLine(OA)) </formalization> <think>According to the problem, we know that AB = OA, and O is the center of circle O. It is common knowledge that both OA and OB are the radii of circle O. From this, we can conclude that triangle BOA is isosceles since OA = OB. Further analysis shows that triangle OAB is also isosceles, leading us to deduce that all three sides of triangle BOA are equal, making it equilateral. Based on the properties of an equilateral triangle, we know that ∠BOA = 60°. Since ∠BOA = ⌒OAB, we find that ⌒OAB = 60°. According to the property of arcs, the angle subtended by the same arc at the circumference is half of the angle at the center. Therefore, we can derive that ∠BDA = ⌒OAB / 2. Substituting the known value of ⌒OAB, we calculate that ∠BDA = 30°. Thus, we have completed the entire solving process. </think> <answer>30</answer> Analyze the input geometry image to extract consCDL and imgCDL, then answer the question. Question: As shown in the diagram, AB=OA, the center of ⊙O is O. Find the measure of ∠BDA.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 287d5368-0433-40f8-a643-9c2d056af455Cited by top-tier papers1
Ask how each one uses itBuilds on12
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
- Making LLaMA SEE and Draw with SEED TokenizerYuying Ge, Sijie Zhao, Ziyun Zeng, Yixiao Ge et al.ICLR 2024 · 202 citations
- UniTok: a Unified Tokenizer for Visual Generation and UnderstandingChuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang et al.NeurIPS 2025 · 164 citations
Related papers
- CogCoM: A Visual Language Model with Chain-of-Manipulations ReasoningJi Qi, Ming Ding, Weihan Wang, Yushi Bai et al.ICLR 2025
- Do Large Language Models Truly Understand Geometric Structures?Xiaofeng Wang, Yiming Wang, Wenhong Zhu, Rui WangICLR 2025
- A Generalized Geometric Theoretical Framework of Centroid Discriminant Analysis for Linear Classification of Multi-dimensional DataYue Wu, Jialin Zhao, Carlo Vittorio CannistraciICLR 2026
- GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-trainingRenqiu Xia, Mingsheng Li, Hancheng Ye, Wenjie Wu et al.ICLR 2025
- A Symbolic Characters Aware Model for Solving Geometry ProblemsMaizhen Ning, Qiu-Feng Wang, Kaizhu Huang, Xiaowei HuangACM MM 2023 · 18 citations
