paper-with-me

Papers

Solving Geometry Problems: Combining Text and Diagram Interpretation

2015-09-01 · EMNLP 2015 9 · Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni, Clint Malcolm
📄 PDF Abstract BibTeX

Code (1)

uwnlp/geosolver 공식 구현

Tasks

Automated Theorem ProvingMathematical Question AnsweringSemantic Parsing

Similar Papers 제목 키워드 기반

A Symbolic Character-Aware Model for Solving Geometry Problems

2023-08-05 · Maizhen Ning, Qiu-Feng Wang, Kaizhu Huang, Xiaowei Huang

AI has made significant progress in solving math problems, but geometry problems remain challenging due to their reliance on both text and diagrams. In the text description, symbolic characters such as "$\triangle$ABC" o…

MathMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONSelf-Supervised Learning

GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions

2025-04-14 · Jo-Ku Cheng, Zeren Zhang, Ran Chen, Jingyang Deng 외

We propose GeoUni, the first unified geometry expert model capable of generating problem solutions and diagrams within a single framework in a way that enables the creation of unique and individualized geometry problems.…

Image Generation

A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram

2023-02-22 · Ming-Liang Zhang, Fei Yin, Cheng-Lin Liu

Geometry problem solving (GPS) is a high-level mathematical reasoning requiring the capacities of multi-modal fusion and geometric knowledge application. Recently, neural solvers have shown great potential in GPS but sti…

Geometry Problem SolvingMathematical Reasoning

GenesisGeo: Technical Report

2025-09-26 · Minfeng Zhu, Zi Wang, Sizhe Ji, Zhengtong Du 외 arxiv

Recent neuro-symbolic geometry theorem provers have made significant progress on Euclidean problems by coupling neural guidance with symbolic verification. However, most existing systems operate almost exclusively in a s…

Visual Grounding

GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation

2025-10-13 · Shasha Guo, Liang Pang, Xi Wang, Yanling Wang 외 arxiv

Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct auxiliary lines via code-driven rendering, a strategy that r…

Reinforcement LearningCode Generation