PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

• URL: http://arxiv.org/abs/2605.30512v1
• Date: Thu, 28 May 2026 19:49:27 GMT
• Title: PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
• Abstract summary: PhyDrawGen is a neuro-symbolic pipeline that decouples semantic scene understanding from physical constraint satisfaction.<n>It significantly outperforms GPT-5-image, Gemini 2.5 Flash, and Gemini 3 Pro, demonstrating robust physical accuracy even on unusual-object problems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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 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.

Related papers

• Towards Physics-Faithful Generation of Scientific Diagrams [60.50428624576465]
  Princigram is a physics-faithful scientific-diagram generator.<n>We present Princigram, a physics-faithful scientific-diagram generator.
  arXiv  Detail & Related papers  (2026-08-13T11:40:33Z)
• Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation [72.04671111142191]
  We introduce Physics Question Scene Graph (PQSG), a hierarchical question-based evaluation pipeline.<n>PQSG evaluates generated videos by checking their faithfulness to a prompt across objects, actions, and adherence to physical laws.<n>We validate PQSG by creating FinePhyEval, a dataset with physics-based prompts and corresponding generated videos.
  arXiv  Detail & Related papers  (2026-06-24T02:12:54Z)
• THOM: Generating Physically Plausible Hand-Object Meshes From Text [44.69476210110844]
  Generation of 3D hand-object interactions (HOIs) from text is crucial for dexterous robotic grasping and VR/AR content generation.<n>We introduce THOM, a training-free framework that generates photorealistic, physically plausible 3D HOI meshes without the need for a template object mesh.<n>THOM consistently surpasses state-of-the-art methods in terms of text alignment, visual realism, and interaction plausibility.
  arXiv  Detail & Related papers  (2026-04-03T05:17:12Z)
• PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment [23.066204478030627]
  Video Models (VDMs) offer a promising approach for simulating dynamic scenes and environments.<n>Existing models often generate temporally incoherent content that violates basic physical intuition.<n>We propose PhysAlign, an efficient framework for physics-coherent image-to-videoI (2V) generation.
  arXiv  Detail & Related papers  (2026-03-14T05:44:18Z)
• PhysGraph: Physically-Grounded Graph-Transformer Policies for Bimanual Dexterous Hand-Tool-Object Manipulation [15.661420962372441]
  Existing methods naively represent the entire system state as a single configuration vector.<n>We present PhysGraph, a physically-grounded graph transformer policy for challenging bimanual hand-tool-object manipulation.
  arXiv  Detail & Related papers  (2026-03-02T04:32:20Z)
• Compressive Recovery of Signals Defined on Perturbed Graphs [4.021249101488848]
  We present an algorithm which simultaneously recovers the signal from the compressive measurements and also corrects the graph perturbations. An application to compressive image reconstruction is also presented, where graph perturbations are modeled as undesirable graph edges linking pixels with significant intensity difference.
  arXiv  Detail & Related papers  (2024-02-12T13:20:52Z)
• A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer [47.25114679486907]
  We introduce GraphsGPT, featuring a Graph2Seq encoder that transforms Non-Euclidean graphs into learnable Graph Words. A GraphGPT decoder reconstructs the original graph from Graph Words to ensure information equivalence.
  arXiv  Detail & Related papers  (2024-02-04T12:29:40Z)
• ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection [84.0718034981805]
  We introduce a novel framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD) In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. In the next stage, the decoders are retrained for detection on the original graph.
  arXiv  Detail & Related papers  (2023-12-22T09:02:01Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning [84.35102534158621]
  We study pre-trained language models that generate explanation graphs in an end-to-end manner. We propose simple yet effective ways of graph perturbations via node and edge edit operations. Our methods lead to significant improvements in both structural and semantic accuracy of explanation graphs.
  arXiv  Detail & Related papers  (2022-04-11T00:58:27Z)
• Equivariant Graph Mechanics Networks with Constraints [83.38709956935095]
  We propose Graph Mechanics Network (GMN) which is efficient, equivariant and constraint-aware. GMN represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency.
  arXiv  Detail & Related papers  (2022-03-12T14:22:14Z)
• My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control [65.77164390203396]
  We present a series of ablations on existing methods that show that morphological information encoded in the graph does not improve their performance. Motivated by the hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing, we also propose Amorpheus.
  arXiv  Detail & Related papers  (2020-10-05T08:37:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.