Skip to content

ZJU-REAL/Easel / skills/builtin/real-lab-paper-promotion

real-lab-paper-promotion

Verified

当用户需要论文小红书宣传稿与忠实截图时,为 REAL Lab AI 论文生成小红书中文宣传文案及与正文对应的原始 PDF 截图。输入本地 PDF、PDF 下载地址、arXiv 链接或编号,输出严格限长的 MD 与截图文件夹;支持修改已有稿件,不用于自动发布或普通长篇论文博客。

FileKindSize
EASEL-META.mdmarkdown1.5 KB
LICENSEother11.1 KB
NOTICEother194 B
README.mdmarkdown1.8 KB
SKILL.mdskill md5.5 KB
agents/openai.yamlconfig329 B
examples/INDEX.mdmarkdown1.1 KB
examples/agent-g2.mdmarkdown1.5 KB
examples/computersd.mdmarkdown1.9 KB
examples/hybridcua.mdmarkdown1.4 KB
examples/spacecast-bench.mdmarkdown2.2 KB
examples/ttpo.mdmarkdown1.7 KB
examples/worldmembench.mdmarkdown2.9 KB
references/style-guidelines.mdmarkdown3.0 KB
references/workflow.mdmarkdown6.3 KB
requirements.txtmanifest16 B
scripts/promotion.pyscript13.9 KB
scripts/test_promotion.pyscript9.1 KB

examples/spacecast-bench.md

View on GitHub
# 物体移动后,AI 能推断新的空间关系吗?

💡 看一张房间的照片,我们能判断桌子在哪、哪个物体被挡住。但移动物体或旋转场景后,空间关系会怎样变化?视觉语言模型能看懂眼前的场景,也能预判这些变化吗? 现有评测大多关注图像中已经呈现的空间关系。我们希望再往前一步,提出了 SpaceCast-Bench,进一步评估模型的预测性空间推理能力:只提供变化前的图像和文字描述的操作,让模型推断变化后的空间关系。 	 🛠 从看懂场景,到推演变化 SpaceCast-Bench 包含来自 ScanNet 和 ScanNet++ 的 182 个真实室内场景、3,862 道题目、16 类任务,分为三个层级: 🔹 L1 静态感知:理解当前的方向、距离、遮挡和附着关系。 🔹 L2 局部预测:移动、旋转或移除一个物体后,相关空间关系如何变化? 🔹 L3 全局预测:旋转整个场景后,从相机、物体和世界等不同参照系判断方向。 通过分层评测,我们希望进一步区分:模型是没看懂初始场景,还是无法正确更新变化后的空间状态? 	 📊 测了 21 个模型,差距仍然明显 在评估的基线模型中,最佳得分为 58.0%,人类达到 87.2%;参与评测的空间专项模型仍接近随机水平。 整体得分为 16 类任务准确率的宏平均。 受控分析还发现:模型对当前空间关系的感知能力,并不能直接转化为对变化后空间关系的预测能力。 	 📈 这种能力可以训练吗? 我们用同一数据构建流程,从与评测集不重叠的场景中生成训练样本。经过分阶段监督微调,Qwen3-VL-4B: ✨ SpaceCast-Bench:34.0% → 65.7% ✨ 六个域外基准宏平均:33.5% → 38.1% 这些结果说明,针对空间状态变化的训练,既能改善预测性空间推理,也能带来一定的跨任务迁移收益。 	 🌱 从理解“现在是什么样”,走向推断“变化后会怎样”,是我们希望继续探索的空间能力。 	 代码和评测数据集已开放,欢迎交流讨论、提交 Issue / PR,也欢迎点个 Star 支持!❤️ 📄 arXiv:2610.12402 💻 Code:ZJU-REAL/SpaceCast-Bench 🤗 Dataset:hongxingli/SpaceCast-Bench
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall