Paper Detail
Zhaohe Liao, Kaixun Jiang, Zhihang Liu, Yujie Wei, Junqiu Yu, Quanhao Li, Hong-Tao Yu, Pandeng Li, Yuzheng Wang, Zhen Xing, Shiwei Zhang, Chen-Wei Xie, Yun Zheng, Xihui Liu
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{liao2026aibench,
title = {AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation},
author = {Zhaohe Liao and Kaixun Jiang and Zhihang Liu and Yujie Wei and Junqiu Yu and Quanhao Li and Hong-Tao Yu and Pandeng Li and Yuzheng Wang and Zhen Xing and Shiwei Zhang and Chen-Wei Xie and Yun Zheng and Xihui Liu},
year = {2026},
abstract = {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 correc},
url = {https://huggingface.co/papers/2603.28068},
keywords = {VQA, VLM, AIBench, visual-logical consistency, logic correctness, aesthetics, test-time scaling, code available, huggingface daily},
eprint = {2603.28068},
archiveprefix = {arXiv},
}
{}