科学图表如何变成LaTeX代码？新基准直击多模态大模型短板。
arXiv:2608.12262v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and…
首个系统评估多模态大模型生成图表注释能力的基准，揭示模型在数据推理与视觉布局上的短板。
arXiv:2608.03464v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have made significant progress in chart understanding, gene…
微软发布Flint可视化语言，专为AI时代设计，让数据图表生成变得简单智能。
Article URL: https://microsoft.github.io/flint-chart/ Comments URL: https://news.ycombinator.com/item?id=49130604 Points: 43 # Comments: 7
研究MLLM生成可视化声明是源于图表数据还是模型知识，为无障碍数据理解开启新视角
arXiv:2607.25021v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can connect visualization patterns to external causes, conseq…
Flint让AI智能体一句话生成专业图表，支持Vega-Lite、ECharts等，开源易集成。
IT之家 7 月 12 日消息，微软研究院联合中国人民大学 IDEAS Lab 联合推出了开源可视化中间语言 Flint，可以让 AI 智能体“一句话生成” Vega-Lite、ECharts、 Chart.js 的可渲染图表。 据介绍，现有可视化库通常提供大量配置选项，若采用精简配置，生成的图表未…
联邦微调藏风险！图表示学习竟能放大模型操纵攻击，LLM安全防线告急。前沿研究不可错过。
arXiv:2605.07961v2 Announce Type: replace Abstract: Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapt…
把纵向医学影像建模成图，用 AI 预判治疗反应，为个性化医疗带来全新可能。
arXiv:2607.04912v1 Announce Type: cross Abstract: In patients with breast cancer, pathological complete response (pCR) has been established as a clini…
受够 Mermaid 一错就崩？Flora 以容错设计让 AI 生成的图表不再因一个小错误变成空白框。
Article URL: https://www.normallydistributed.dev/introducing-flora-a-diagram-library-built-with-and-for-ai/ Comments URL: https://news.ycombinator.com…
多模态大模型提取图表数据常不可靠？CHI'26论文推出专用基准与训练框架，显著提升提取准确性。
arXiv:2606.29808v1 Announce Type: cross Abstract: Chart data extraction, which reverse-engineers data tables from chart images, is essential for repro…
从零实现实时协作图表画布，React + Go 后端如何搞定节点扰动与缓存机制
I wanted a fast way to sketch architecture diagrams and share them with other people live, without installing anything and without the heavy, corporat…
教AI和人类用Matplotlib做出不丑的图表，Tufte风格+实战代码，看完直接升级你的可视化。
https://github.com/temataro/better-graphs I want to teach good Matplotlib taste to agents and humans. This repo contains: 1. Agent instructions + desi…
原生高性能金融图表库，专为数据密集场景打造，开发者福音。
Article URL: https://github.com/efixdata/exeria-charts Comments URL: https://news.ycombinator.com/item?id=48641395 Points: 1 # Comments: 0
Java声明式引擎，让结构化PDF与矢量图表的生成变得简单优雅。
Article URL: https://github.com/DemchaAV/GraphCompose Comments URL: https://news.ycombinator.com/item?id=48618028 Points: 3 # Comments: 0
表格数据一键变会说话的数据视频，动态图表加语音解说让洞察一目了然
arXiv:2606.20388v1 Announce Type: cross Abstract: Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate da…
科研论文配图难？用AI快速将摘要、机制描述转化为视觉草稿，支持迭代优化，大幅提升制图效率。
Article URL: https://scifigureai.com Comments URL: https://news.ycombinator.com/item?id=48565185 Points: 2 # Comments: 0
将枯燥文本转化为交互式概念图，帮你快速理解复杂知识，告别信息过载
These days we are full of information and we spend hours reading, researching and linking the dots. Grops helps you do this in half of the time withou…
跨语言越狱检测新突破：不依赖语言特征，学习意图表示，有效识别多种语言下的越狱攻击。
arXiv:2606.11202v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in applications for global multilingual users, …
一个Agent技能，利用HTML生成美观交互式图表，开源项目值得尝试。
Article URL: https://github.com/plannotator/effective-html Comments URL: https://news.ycombinator.com/item?id=48469576 Points: 2 # Comments: 0
集成聊天与邮件的Markdown笔记工具，支持嵌入公式和D3图表，助力团队高效协作
Article URL: https://github.com/ThGSoft/NotesPro Comments URL: https://news.ycombinator.com/item?id=48427217 Points: 2 # Comments: 2
用图表示代替自由文本描述Agent技能，提升可靠性并简化创建与改进流程。
arXiv:2606.04781v1 Announce Type: new Abstract: Agent Skills today consist largely of free-form prose requiring the agent to read, interpret, and re-d…