大模型当“结构工程师”：用LLM驱动图生成，让局部优化方法更聪明。
arXiv:2608.13333v1 Announce Type: new Abstract: Large neighborhood search normally selects a random subset of decision variables for iterative optimiz…
一键生成LinkedIn味儿十足的职场鸡汤帖，专治“正能量”尴尬症，娱乐价值拉满
Article URL: https://www.cringebot3000.com/ Comments URL: https://news.ycombinator.com/item?id=49268564 Points: 447 # Comments: 192
把大图生成难题“揉碎”再扩散，用图极限实现高效可扩展的图生成新方法，专治算力焦虑。
arXiv:2607.07232v1 Announce Type: cross Abstract: Diffusion models represent a leading paradigm for graph generation, with notable impact in domains s…
AWS新手必看！用“魔法助手”比喻S3事件触发，轻松理解文件上传后的自动处理机制。
👦 Nephew: Uncle, when a file finishes uploading to S3... nothing happens to it after that. Shouldn't something make a thumbnail, or check the file is …
一键将X帖子转化为精美轮播图，适合内容创作者快速复用社交内容，AI智能排版省时省力。
Made this for my usage: paste a link or threads, the platform will read the post, parse data, analyze then turns into platform-specific carousels with…
把视频模型当先验来画顺序素描，跨界思路让生成更连贯自然。
arXiv:2602.15819v2 Announce Type: replace Abstract: Sketching is inherently sequential: strokes are drawn progressively to explore and refine ideas. Y…
大语言模型赋能模拟集成电路设计，打通从设计意图到布局生成的自动化链路
arXiv:2606.15052v1 Announce Type: cross Abstract: Traditional design of analog circuits heavily relies on manual interventions across topology, sizing…
IT之家 6 月 16 日消息，华为 nova 15 系列手机开启了鸿蒙 HarmonyOS 6.1.0.125 SP10 版本升级，系统包大小约 2.85GB。据介绍，本次更新图库 AI 沾色将支持为逆光人物图一键生成剪影效果，同时优化了系统性能和部分应用的使用体验。 IT之家附华为 nova 1…
用LLM生成图结构，实现多工具查询执行的高可靠规划，为复杂查询任务带来新思路。
arXiv:2606.08300v1 Announce Type: new Abstract: Many real-world queries over personal data span multiple applications and require structured planning,…
新方法通过不确定性校准提升3D分子图生成的可靠性，有望推动药物发现与材料设计。
arXiv:2606.01595v1 Announce Type: new Abstract: Bayesian inference provides a principled framework for modeling epistemic uncertainty in neural networ…
用自然语言描述电路需求，AI自动生成PCB原理图，开启硬件设计新范式
arXiv:2606.01188v1 Announce Type: cross Abstract: Translating natural-language hardware requirements into correct printed circuit board (PCB) schemati…
一篇关于图生成模型的论文，提出置换不变的谱扩散方法，用Dyson扩散统一处理图表示，提升生成质量。
arXiv:2510.08535v2 Announce Type: replace-cross Abstract: Diffusion models are central to generative modeling and have been adapted to graphs by diffu…
利用语义代码表示直接生成PCB原理图，开创AI自动化电路设计新路径。
arXiv:2605.30345v1 Announce Type: new Abstract: Printed circuit board (PCB) schematic design defines nearly all electronic hardware, but it remains ma…
用自然语言描述就能自动生成电路原理图，多智能体LLM框架为硬件设计带来新可能
arXiv:2601.04505v3 Announce Type: replace Abstract: Generating accurate circuit schematics from high-level natural language descriptions remains a per…
布局约束文本转SVG图生成新方案，用强化学习结合几何感知，精准控制输出结构
arXiv:2605.25447v1 Announce Type: new Abstract: Generating structured, editable diagrams remains a significant challenge for contemporary large langua…
利用大语言模型学习超图结构，实现可编辑性更强的平面图自动生成新方法。
arXiv:2605.18932v1 Announce Type: new Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation bas…
提出首个统一框架，用强化学习后训练攻克分子图生成的可控性难题，解决原子级动作空间和化学无效中间态问题
arXiv:2605.15354v1 Announce Type: new Abstract: Despite the success of foundation models in language and vision, molecular graph generation still lack…