DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing

• URL: http://arxiv.org/abs/2607.02290v1
• Date: Thu, 02 Jul 2026 15:07:47 GMT
• Title: DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
• Abstract summary: We introduce DisciplineGen-1M, a million-scale dataset that supports text-to-image generation and image editing.<n>It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports.<n>Building on DisciplineGen-1M, we introduce a discipline-informed reasoning-generation model for both text-to-image generation and image editing.
• Score: 65.66783293569955
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose correctness depends on disciplinary concepts, symbolic structure, and precise spatial relations. We introduce DisciplineGen-1M, a million-scale multidisciplinary dataset that supports text-to-image generation and image editing. It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports. To construct the dataset, we design a scalable framework that combines vector-graphics rendering, OCR-based editing, curated programmatic synthesis, and large-scale text-to-image filtering. These pipelines produce captions, editing instructions, structured annotations, and paired images with controllable semantic differences. Building on DisciplineGen-1M, we further introduce a discipline-informed reasoning-generation model for both text-to-image generation and image editing. Experiments on discipline-related benchmarks, GenExam and GRADE, show substantial improvements over open-source baselines, while evaluations on general reasoning-informed benchmarks, WISE and RISE, further indicate broader transfer. The results suggest that large-scale structured academic visual data is a key ingredient for moving image generation from aesthetic plausibility toward verifiable knowledge-grounded visual creation. We will publicly release our dataset, model, and source code of the data curation pipeline to ensure reproducibility and benefit future research.

Related papers

• ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs [51.31488026676001]
  We propose a framework that exploits factual information from a knowledge graph via retrieval-augmented generation (RAG)<n>Specifically, our method alternates between answer generation and knowledge-graph retrieval, and controls the search using a correctness judgment.<n>We show experimentally that it improves the level of detail of artwork explanations and reduces the retrieval cost of external knowledge.
  arXiv  Detail & Related papers  (2026-09-01T03:08:14Z)
• S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing [25.725824689793402]
  We present an open-weight unified multimodal model for scientific image understanding, generation, and editing.<n>S1- Omni-Image builds on the scientific multimodal reasoning backbone S1-VL-32B.<n>It supports scientific image understanding, generation, and editing in a unified framework.
  arXiv  Detail & Related papers  (2026-06-23T11:19:34Z)
• Semantic-Structural Alignment for Generative Pictorial Charts [59.45629259524998]
  We present a generative framework for the automated synthesis of pictorial charts.<n>We frame the problem as a dual-conditioned generation task guided by two parallel external control signals.<n>Our method produces pictorial charts that are both artistically compelling and structurally consistent.
  arXiv  Detail & Related papers  (2026-05-05T05:20:46Z)
• Charts Are Not Images: On the Challenges of Scientific Chart Editing [66.38730113476677]
  textitFigEdit is a benchmark for scientific figure editing comprising over 30,000 samples.<n>Our benchmark demonstrates the profound limitations of pixel-level manipulation.<n>By releasing textitFigEdit, we aim to enable systematic progress in structure-aware figure editing.
  arXiv  Detail & Related papers  (2025-11-30T06:13:48Z)
• Factuality Matters: When Image Generation and Editing Meet Structured Visuals [46.627460447235855]
  We construct a large-scale dataset of 1.3 million high-quality structured image pairs.<n>We train a unified model that integrates a VLM with FLUX.1 Kontext.<n>A three-stage training curriculum enables progressive feature alignment, knowledge infusion, and reasoning-augmented generation.
  arXiv  Detail & Related papers  (2025-10-06T17:56:55Z)
• Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
  We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
  arXiv  Detail & Related papers  (2025-09-08T17:56:23Z)
• OCR-VQGAN: Taming Text-within-Image Generation [4.5718306968064635]
  We present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss. We demonstrate the effectiveness of OCR-VQGAN by conducting several experiments on the task of figure reconstruction.
  arXiv  Detail & Related papers  (2022-10-19T16:37:48Z)
• Re-Imagen: Retrieval-Augmented Text-to-Image Generator [58.60472701831404]
  Retrieval-Augmented Text-to-Image Generator (Re-Imagen) Retrieval-Augmented Text-to-Image Generator (Re-Imagen)
  arXiv  Detail & Related papers  (2022-09-29T00:57:28Z)

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.