paper-with-me

홈 › Papers

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

2026-05-28 · Nafiul Haque, Syed Nazmus Sakib, Shifat E Arman arxiv

Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, they systematically hallucinate force vectors, ignore conservation laws, and violate geometric constraints. We present PhyDrawGen, a neuro-symbolic pipeline that decouples semantic scene understanding from physical constraint satisfaction. First, a large language model extracts a typed scene graph from the problem text. A deterministic solver then converts this graph into a Planar Straight-Line Graph (PSLG), encoding force balance, optical paths, and field topologies as exact geometric primitives. Finally, a fine-tuned Qwen-VL model implements a visually grounded propose-verify loop to iteratively correct any constraint violations. Evaluated on a benchmark of 1,449 problems spanning mechanics, optics, and electromagnetism, PhyDrawGen significantly outperforms GPT-5-image, Gemini 2.5 Flash, and Gemini 3 Pro, demonstrating robust physical accuracy even on unusual-object problems.

📄 PDF Abstract BibTeX arXiv:2605.30512

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Understanding

Similar Papers 제목 키워드 기반

Towards Physics-Faithful Generation of Scientific Diagrams

2026-08-13 · Minghui Zhang, Jinxin Shi, Yifan Chang, Liangliang Zhao 외 arxiv

Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct fo…

Text-to-Image Generation

GeoLoom: High-quality Geometric Diagram Generation from Textual Input

2025-12-09 · Xiaojing Wei, Ting Zhang, Wei He, Jingdong Wang 외 arxiv

High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geome…

GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs

2026-03-23 · Achmad Anggawirya Alimin, Artur M. Schweidtmann arxiv

Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) and knowledge graphs offer new opportunities for interacting with engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs). …

Knowledge Graphs

VeriGeo: Controllable Geometry Question Generation with Numerical and Analytical Verification

2026-06-12 · Xiaoxian Duan, Zequn Liu, Yingce Xia arxiv

Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because the problem statement, diagram, constraints, and solution should be …

Mathematical ReasoningQuestion Generation

FATE: Closed-Loop Feasibility-Aware Task Generation with Active Repair for Physically Grounded Robotic Curricula

2026-03-02 · Bingchuan Wei, Bingqi Huang, Jingheng Ma, Zeyu zhang 외 arxiv

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physicall…