提出关联递归记忆方法，让大模型上下文窗口突破长度限制，高效处理超长序列
arXiv:2607.11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applica…
NVIDIA官方详解硬件感知的大模型设计，平衡吞吐量与延迟的Pareto前沿策略。
Article URL: https://developer.nvidia.com/blog/ai-model-co-design-hardware-friendly-llm-design/ Comments URL: https://news.ycombinator.com/item?id=488…
Go 开发者探讨 ORM 新期望：如何平衡 SQL 控制权与查询简化？
I have been working on a Go ORM and I am trying to understand what experienced Go developers actually want from an ORM. The main problems I see: - los…
扔掉Transformer和显卡，纯CPU拓扑AI架构让LLM高效运行，开源方案值得关注。
Article URL: https://www.hackster.io/jenfi59/brainiak-topological-al-drives-llm-by-lora-runtime-adapters-73a678 Comments URL: https://news.ycombinator…
Terraform风格定义AI代理的配置工具，用Go+Python实现，支持OpenAI和Tavily。
Article URL: https://github.com/weirdGuy/kastor Comments URL: https://news.ycombinator.com/item?id=48833183 Points: 2 # Comments: 0
三大AI模型ChatGPT、Gemini、Claude核心差异一图看懂，从自注意力机制到各自架构特点。
In this article, we will look at the various architectural forks the teams building these models encountered and the decisions they took.
AI法律初创公司Norm获1.2亿美元C轮融资，估值超10亿美元，展现法律科技赛道热度。
AI law startup Norm has raised a $120 million Series C round led by Khosla Ventures, valuing the startup at $1.2 billion.
Prisma 无法在浏览器运行？这个新开源 ORM 让你在浏览器、Expo、React Native 里直接操作数据库，兼容 DuckDB、IndexedDB 等。
I love Prisma. I have shipped Prisma to production more times than I care to count. It changed how a lot of us write TypeScript against databases. But…
一文讲透Python ORM中的N+1陷阱，用代码实例教你用select_related/prefetch_related告别性能灾难。
Introduction Python's ORMs — SQLAlchemy and the Django ORM — are a joy to write and dangerously easy to make slow. A loop over a queryset that reads o…
一篇聚焦提示优化新范式的论文，提出对比反思机制实现迭代改进，为AI代理的信息检索场景提供创新方案。
arXiv:2606.30840v1 Announce Type: new Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize ans…
Transformer遇上自动化规划，对称性感知训练让AI规划更高效精准。
arXiv:2508.07743v2 Announce Type: replace Abstract: While transformers excel in many settings, their application in the field of automated planning is…
一行import即可加速MoE微调3.7倍，英伟达开源NeMo AutoModel，降低内存占用超30%，轻松提升训练效率。
在Transformers v5的基础上，增加了专家并行、DeepEP和TransformerEngine
基于LLM的两阶段Transformer框架，攻克工业轴承故障诊断中数据异质、工况变化和标签稀缺的并发难题。
arXiv:2606.24459v1 Announce Type: new Abstract: Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition vari…
用视觉直观解释Transformer核心原理，非技术背景也能轻松理解GPT工作机制，适合分享给好奇的朋友。
I have had a few conversations in the past year with non-technical folks (traditional finance types, consultants) who asked for a simple explainer on …
Transformer论文作者、Gemini联席负责人从谷歌跳槽OpenAI，奥尔特曼亲自欢迎，AI人才大战再添重磅一局。
IT之家 6 月 20 日消息，谷歌前工程副总裁、Gemini 技术联席负责人诺姆 · 沙泽尔宣布离职，转投 OpenAI。 IT之家获悉，当地时间 18 日，沙泽尔在 X 上宣布，离开谷歌是一个艰难决定，他为谷歌团队以及团队共同取得的成果感到自豪，“很高兴与大家分享，我将加入 OpenAI，也期待…
全球首个人形机器人通用小脑，2万小时人类动作数据训练，实现零样本泛化，堪比机器人界的“GPT时刻”。
人形机器人正式迈入“GPT时代”
利用对称性隐私保护新范式，正交等变Transformer让大模型推理更安全
arXiv:2606.16461v1 Announce Type: new Abstract: Running large language models locally is often impractical, pushing inference on sensitive text to thi…
用Transformer引导图注意力网络直接重建心脏网格，告别传统繁琐工作流，数字孪生更高效。
arXiv:2606.13188v1 Announce Type: cross Abstract: Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting thos…
用降维技术揭示大模型内部隐藏的几何结构，直观理解语言模型如何表征知识。
arXiv:2511.21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, …
揭秘Transformer缩放定律背后的学习动力学与泛化机制，87页长文深度统一理论框架。
arXiv:2512.22088v3 Announce Type: replace-cross Abstract: The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improveme…