PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
Quick Answer
PhyDrawGen is a neuro-symbolic model that generates physics diagrams from natural language while adhering to physical laws.
Quick Take
It outperforms GPT-5-image, Gemini 2.5 Flash, and Gemini 3 Pro on a benchmark of 1,449 problems in mechanics, optics, and electromagnetism, demonstrating superior physical accuracy.
Key Points
- Decouples semantic understanding from physical constraint satisfaction.
- Uses a to extract typed scene graphs.
- Converts scene graphs into Planar Straight-Line Graphs (PSLG) for accurate geometry.
- Implements a propose-verify loop with a fine-tuned Qwen-VL model.
- Demonstrates robust performance on unusual-object problems.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2605. 30512v1 Announce Type: new Abstract: 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 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.