AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908923327414272 |
|---|---|
| author | Liao, Zhaohe Jiang, Kaixun Liu, Zhihang Wei, Yujie Yu, Junqiu Li, Quanhao Yu, Hong-Tao Li, Pandeng Wang, Yuzheng Xing, Zhen Zhang, Shiwei Xie, Chen-Wei Zheng, Yun Liu, Xihui |
| author_facet | Liao, Zhaohe Jiang, Kaixun Liu, Zhihang Wei, Yujie Yu, Junqiu Li, Quanhao Yu, Hong-Tao Li, Pandeng Wang, Yuzheng Xing, Zhen Zhang, Shiwei Xie, Chen-Wei Zheng, Yun Liu, Xihui |
| contents | Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28068 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation Liao, Zhaohe Jiang, Kaixun Liu, Zhihang Wei, Yujie Yu, Junqiu Li, Quanhao Yu, Hong-Tao Li, Pandeng Wang, Yuzheng Xing, Zhen Zhang, Shiwei Xie, Chen-Wei Zheng, Yun Liu, Xihui Computer Vision and Pattern Recognition Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task. |
| title | AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.28068 |