English(EN) Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

新AI框架SPIRE通过逆向规划解决幻灯片个性化问题

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-01 00:00

研究人员开发了SPIRE，一个用于代理幻灯片生成的新框架，通过将页面级个性化视为一个逆向规划问题来解决。这种方法可以在无需了解具体工具（如PowerPoint或Beamer）的情况下学习潜在的设计意图。SPIRE采用多智能体强化学习策略，其中两个智能体通过去噪故意损坏的视觉结构来协同优化设计，这种方法已被证明是实现个性化的可靠替代方案，并能降低策略梯度方差。 AI

影响这项研究可能催生出能够执行细致设计任务的更复杂的AI智能体，从而改善演示软件的用户体验。

排序理由该集群描述了一篇详细介绍新AI框架和方法的论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Tianci Liu, Zihan Dong, Linjun Zhang, Haoyu Wang, jing Gao, Emre Kiciman, Ranveer Chandra, Wei-Ting Chen · 2026-07-02 04:00

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

arXiv:2607.00407v1 Announce Type: new Abstract: Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespecified templates or user verbose instructions, they fa…
Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-01 00:00

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

Page-level slide personalization is addressed through a novel framework that formulates the problem as inverse planning and uses a multi-agent reinforcement learning approach to learn design intents without requiring specific tool knowledge.

报道来源 [2]

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

相关实体

相关话题