Towards Physics-Faithful Generation of Scientific Diagrams

• URL: http://arxiv.org/abs/2608.13112v1
• Date: Thu, 13 Aug 2026 11:40:33 GMT
• Title: Towards Physics-Faithful Generation of Scientific Diagrams
• Abstract summary: Princigram is a physics-faithful scientific-diagram generator.<n>We present Princigram, a physics-faithful scientific-diagram generator.
• Score: 60.50428624576465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on web imagery with physically shallow captions, generic models produce diagrams that look plausible but are physically wrong, harmful in education and scientific communication. We present Princigram, a physics-faithful scientific-diagram generator, and its data pipeline. Our central advance is Structured Physical Chain-of-Thought (SP-CoT): a per-subdiscipline schema that decomposes a physics diagram into an explicit multi-step reasoning chain across six subdisciplines, from scene identification through force or process analysis to governing laws and synthesis. Unlike free-form chain-of-thought, SP-CoT follows a fixed schema with strict fidelity rules that separate visually grounded facts from physically inferred reasoning and type all mathematics symbolically; it serves both as dense training supervision and, at inference, as a structured "thinking" prompt. With it we curate and structurally annotate 4.3 million physics images, of which 115,037 carry expert-level annotation, and adapt a unified multimodal backbone. We further introduce VeriphyT2IBench, whose questions are derived from each held-out diagram's own structured annotation: each diagram becomes an item-specific bank of binary questions about its objects, forces, and states, so a judge model's score decomposes into named physical facts rather than one holistic number. On the physics subset of GenExam and on VeriphyT2IBench, Princigram shows that explicit physics-structured supervision improves the physical faithfulness of generated scientific diagrams.

Related papers

• From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding [0.0]
  Vision-language models (VLMs) have demonstrated strong performance in visual question answering with natural images.<n>We introduce a framework for generating large-scale diagram-grounded instruction data by leveraging terminology derived from scientific curricula.<n>We construct SciGram, a dataset of over 194K diagrams and 1.4M visual instructions across life, earth, and physical sciences.
  arXiv  Detail & Related papers  (2026-09-01T09:07:31Z)
• Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning [48.21630532401797]
  We reformulate PPVG as event-centric generation by representing physical evolution as a chain of causally connected and physically constrained events.<n>Our framework generates videos with superior physical plausibility across diverse domains.
  arXiv  Detail & Related papers  (2026-09-01T03:35:02Z)
• PhyDrawGen: Physically Grounded Diagram Generation from Natural Language [0.0]
  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.
  arXiv  Detail & Related papers  (2026-05-28T19:49:27Z)
• The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench [30.054788656949636]
  We introduce scientific alignment as an implicit objective for representation learning in scientific domains.<n>We study a principled, testable aspect of scientific alignment through structural isomorphism.<n>We release TC-Bench, a global, reproducible benchmark dataset with an automated construction pipeline for tropical cyclone research.
  arXiv  Detail & Related papers  (2026-05-23T23:51:19Z)
• FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning [11.098160996983417]
  We introduce FeynmanBench, the first benchmark centered on Feynman diagram tasks.<n>It is designed to evaluate AI's capacity for multistep diagrammatic reasoning.<n>Our database spans the electromagnetic, weak, and strong interactions of the Standard Model.
  arXiv  Detail & Related papers  (2026-04-04T23:18:58Z)
• ProPhy: Progressive Physical Alignment for Dynamic World Simulation [55.456455952212416]
  ProPhy is a Progressive Physical Alignment Framework that enables explicit physics-aware conditioning and anisotropic generation.<n>We show that ProPhy produces more realistic, dynamic, and physically coherent results than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-05T09:39:26Z)
• Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery [98.58830663687911]
  VIPERR-aq1 is a multimodal model that performs Visual Induction for Equation Reasoning.<n>It integrates visual perception, trajectory data, and symbolic reasoning to emulate the scientific discovery process.<n>It consistently outperforms state-of-the-art VLM baselines in accuracy and interpretability.
  arXiv  Detail & Related papers  (2025-08-24T14:34:21Z)
• Physics-Encoded Graph Neural Networks for Deformation Prediction under Contact [87.69278096528156]
  In robotics, it's crucial to understand object deformation during tactile interactions. We introduce a method using Physics-Encoded Graph Neural Networks (GNNs) for such predictions. We've made our code and dataset public to advance research in robotic simulation and grasping.
  arXiv  Detail & Related papers  (2024-02-05T19:21:52Z)
• Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models [86.25460882547581]
  We introduce the PHYsical Concepts Inference NEtwork (PHYCINE), a system that infers physical concepts in different abstract levels without supervision. We show that object representations containing the discovered physical concepts variables could help achieve better performance in causal reasoning tasks.
  arXiv  Detail & Related papers  (2023-03-03T11:52:21Z)
• RL-CSDia: Representation Learning of Computer Science Diagrams [25.66215925641988]
  We construct a novel dataset of graphic diagrams named Computer Science Diagrams (CSDia) It contains more than 1,200 diagrams and exhaustive annotations of objects and relations. Considering the visual noises caused by the various expressions in diagrams, we introduce the topology of diagrams to parse topological structure.
  arXiv  Detail & Related papers  (2021-03-10T07:01:07Z)

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.