From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 17 references that are in the map. First posted on arXiv 15 Sep 2026.
Builds on
15 of 17 references.
References · 15
- 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 366
- 2025DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Researchcited by 114
- 2025ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agentscited by 84
- 2021D2S: Document-to-Slide Generation Via Query-Based Text Summarizationcited by 50
- 2017Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Modelscited by 18
- 2025P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmarkcited by 17
- 2024SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posterscited by 14
- 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMscited by 11
- 2026EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detectioncited by 9
- 2025PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generationcited by 8
- 2025Human-Agent Collaborative Paper-to-Page Craftingcited by 7
- 2026Any2Poster: Any-Source Poster Generation Across Modalities and Domainscited by 5
3 more
- 2026PosterHarness: Turning Scientific Poster Generation into an Auditable Instruction-Following Benchmarkcited by 3
- 2026ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blogcited by 2
- 2025SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posterscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs
- 2025Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
- 2025SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts
- 2026ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts
- 2026Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
- 2026PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation
- 2026SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation
- 2026MaLiang-Harness: A Programmable Path to Image and Video Generation