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…
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.
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…
聚焦Tenstorrent Tensix架构的LLM推理瓶颈，提出RMSNorm与矩阵乘融合的算子优化策略，提升数据局部性。
arXiv:2606.09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix arc…
揭秘新型注意力机制：动态线性注意力，同时提升效率与精度，ICML 2026录用论文。
arXiv:2606.10650v1 Announce Type: cross Abstract: The scalability of Large Language Models (LLMs) to long contexts is fundamentally constrained by the…
基于Transformer的多视角架构AQIFormer，实现跨城市空气质量精准分类，创新融合计算机视觉与时空建模。
arXiv:2606.07648v1 Announce Type: new Abstract: Air pollution represents one of the most critical environmental and public health challenges globally,…
突破PreNorm与PostNorm的困境：SpanNorm在提升深度Transformer训练稳定性同时保持高性能
arXiv:2601.22580v2 Announce Type: replace-cross Abstract: The success of Large Language Models (LLMs) hinges on the stable training of deep Transforme…
Transformer一致性训练机制，通过堆叠层间约束提升模型表现与稳定性。
arXiv:2606.05817v1 Announce Type: cross Abstract: Consistency training encourages models to behave similarly across different contexts, and has shown …
GPT风格Transformer在十亿级运动数据上预训练，实现零样本全身运动跟踪。
arXiv:2606.03985v1 Announce Type: cross Abstract: We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale …
面向开发者的AI工程指南，从统计语言模型到基础模型，讲透LLM的演进与工程化实践。
Article URL: https://www.lucavall.in/blog/ai-engineering-for-developers Comments URL: https://news.ycombinator.com/item?id=48366525 Points: 1 # Commen…