The process of transforming raw research data into a coherent manuscript draft remains a fragmented, labor-intensive workow that typically requires prociency across multiple specialized toolsstatistical software (SPSS, R, Python), spreadsheet editors, word processors, and typesetting systems (LaTeX). This fragmentation creates signicant barriers for researchers, particularly those with limited statistical training or those working across language boundaries. In this paper, we present Data2Paper, an AI-assisted system that integrates the pipeline from raw survey or clinical data to a formatted research paper draft. Our system implements four stages: (1) Intelligent Data Cleaning, which detects and handles survey-specic structures such as Likert scales, skip logic, and coded responses; (2) Research Framing, which proposes research questions and hypotheses from the observed data characteristics; (3) Automated Statistical Analysis, in which statistical methods are selected and executed using deterministic Python libraries with LLM support for planning and code generation; and (4) Multilingual Paper Drafting, which assembles results, tables, gures, and citations into a complete manuscript draft in seven languages. We report an internal evaluation on 50 survey and clinical datasets, comparing computed statistics and method choices against expert analyses and collecting quality assessments from 15 researchers. On this benchmark, Data2Paper achieves high agreement with expert-computed statistics and typically completes end-to-end processing within 30 minutes for the evaluated workloads. These results suggest that the system can substantially accelerate early-stage quantitative reporting, although human review remains necessary for domain framing, causal interpretation, and submission readiness. System access and project information are available at https://datatopaper.com.

Patent drawings are a mandatory component of most patent applications, yet their preparation remains one of the most time-consuming and costly steps in the patent prosecution workflow. Professional patent illustrators typically charge $50-$150 per figure, with turnaround times ranging from several days to multiple weeks. At the same time, patent drawings are governed by formal requirements that differ substantially from those of natural images, marketing graphics, and conventional scientific illustrations. This paper presents a structured comparison of drawing requirements across five major patent offices (USPTO, EPO, CNIPA, JPO, and KIPO), proposes a taxonomy of patent figure types informed by a manual review of 500 U.S. patent documents, and identifies the technical challenges that make patent figure generation a distinct multimodal systems problem. We also provide a feature-oriented comparison of existing tools and a system description of PatentFig (https://patentfig.ai), a domain-specific platform for generating patent-oriented figures through structured prompting and iterative refinement. The empirical component is framed as a case-study analysis rather than a benchmark: the case studies and checklist-based scores are intended to highlight representative strengths and failure modes, not to establish definitive performance claims. By making the study design, scope, and limitations explicit, the paper aims to support more reproducible datasets and evaluation protocols for AI-assisted patent figure generation.

KEYWORDS: AI-generated figures, scientific illustration, academic publishing policy, generative AI, reproducibility, SciDraw