从瞬时提示到持续控制：基于递归语义-几何契约的学术海报生成
From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
浏览论文内容
中文总结 AI 辅助
PosterVisor通过语义-几何契约和递归契约执行，将海报生成从瞬时提示转为持续控制，在Paper2Poster基准上显著提升生成质量与人类偏好。
中文摘要 AI 辅助
学术海报生成将多模态论文提炼为单页视觉制品，在固定空间预算下强制要求在信息覆盖度与可读性之间做出严格权衡。现有方法将计划作为瞬时提示传递，并孤立地验证各个阶段，这种策略导致需求在内容与布局模块之间发生漂移，且先前的检查被静默失效。我们提出PosterVisor，一个将海报生成从瞬时提示转变为持续控制的控制框架。编排器（Orchestrator）将评分标准锚定在论文与视觉资产中，将其编译为语义-几何契约（SGC），该契约将主张与来源绑定到所需的视觉元素、预算和空间承诺上。只有完全实例化的记录才成为可执行的断言；其他可用需求仍作为软性指导。递归契约执行（RCE）在证据出现时动态触发跨阶段的检查。关键在于，在修复过程中，RCE会重新检查受影响的检查点状态，防止修复引发的回归静默传播。我们在HTML/CSS和可编辑的PPTX生成器中实例化了PosterVisor。在包含100篇论文的Paper2Poster基准上，PosterVisor-PPT在观察到的平均海报接地QA准确率上优于PosterGen（64.47%对比58.53%），并且在72.5%的非平局成对比较中（95%置信区间，61.6-83.4%）被人类评审员优先选择。一项包含30篇论文的次要研究也在VLM总体和PaperQuiz均值上取得了更高结果。这些结果支持了基于评分标准编译的契约和阶段条件执行，用于可控的海报合成。
英文摘要
Scientific poster generation distills a multimodal paper into a single-page visual artifact, forcing strict trade-offs between informational coverage and readability under a fixed spatial budget. Existing methods pass plans as transient prompts and validate individual stages in isolation. This strategy causes requirements to drift across content and layout modules, and previous checks to be silently invalidated. We introduce PosterVisor, a control framework that shifts poster generation from transient prompts to persistent control. An Orchestrator grounds rubrics in the paper and visual assets, compiling them into a Semantic-Geometric Contract (SGC) that binds claims and sources to required visuals, budgets, and spatial commitments. Only fully instantiated records become executable assertions; other usable requirements remain soft guidance. Recursive Contract Enforcement (RCE) dynamically triggers checks across stages as evidence emerges. Crucially, during repairs, RCE rechecks affected checkpoint states, preventing repair-induced regressions from propagating silently. We instantiate PosterVisor in HTML/CSS and editable PPTX generators. On the 100-paper Paper2Poster benchmark, PosterVisor-PPT improves observed mean poster-grounded QA accuracy over PosterGen (64.47% vs. 58.53%) and is preferred by human judges in 72.5% of non-tied pairwise comparisons (95% CI, 61.6-83.4%). A secondary 30-paper study also yields higher VLM Overall and PaperQuiz means. These results support rubric-compiled contracts and stage-conditioned enforcement for controllable poster synthesis.
发表机构
- Baidu Inc.（百度公司）
- Harbin University of Science and Technology（哈尔滨理工大学）
- Shandong University（山东大学）
- East China Normal University（华东师范大学）
- Soochow University（苏州大学）
机构由 AI 辅助整理，请以论文原文为准。
