DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
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 fra
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorZhaokai Wang →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorMingxin Liu →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorZirun Zhu →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorZiqian Fan →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorYiguo He →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorMohan Zhang →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorLeyao Gu →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorXiangyu Zhao →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorNing Liao →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorShaofeng Zhang →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorXuanhe Zhou →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorZhihang Zhong →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorJunchi Yan →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
- Linked via arxiv authorXue Yang →
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing