Next.js官方分享为AI Agent优化框架的实践，揭秘MCP集成及从Agent视角改进开发体验的幕后思考。
How we built and sunset an in-browser agent, shipped MCP integration, and learned that better AI agent support means thinking from the agent's perspec…
Nuxt 4.2 官方发布，带来实验性 TypeScript 插件、开发错误处理优化及数据请求 AbortController 支持，提升前端开发体验。
Nuxt 4.2 is out - with experimental TypeScript plugin support, better error handling in development, abort control for data fetching, and more!
Nuxt官方发布全新图标组件v1，解决SSR兼容与动态加载难题，提升前端开发效率。
Discover Nuxt Icon v1 - a modern, versatile, and customizable icon solution for your Nuxt projects.
Tailwind CSS 官方发布首个全功能 React UI 套件 Catalyst，内置丰富组件与优雅 API，助力快速构建应用界面
We just released the first development preview of Catalyst, our new fully-componentized, batteries-included application UI kit for React.
React官方发布View Transitions和Activity两项实验性功能，助力前端动画与活动管理，开发者必看！
In React Labs posts, we write about projects in active research and development. In this post, we're sharing two new experimental features that are re…
Node.js 21 正式发布，带来稳定 fetch、WebSocket 客户端、V8 11.8 及实验性模块默认类型等重磅更新。
如何让大模型理解高性能计算？这篇论文用领域自适应和RAG打造HPC专属LLM，实用又前沿。
arXiv:2605.16347v1 Announce Type: new Abstract: Modern scientific research increasingly depends on High-Performance Computing (HPC) infrastructures, y…
深度揭秘权重衰减对训练稳定性的真实作用，挑战传统正则化认知。
arXiv:2605.16622v1 Announce Type: new Abstract: In modern deep learning, weight decay is often credited with "stabilizing" training dynamics, divergin…
利用化学结构-活性分析，实现跨领域分子关系学习，突破传统只关注单一领域的局限。
arXiv:2605.16799v1 Announce Type: new Abstract: Recent advances in molecular representation integrates molecular topological and visual modalities, op…
提出LEAP可学习端到端自适应剪枝方法，在保持大语言模型性能的同时实现高效压缩
arXiv:2605.17289v1 Announce Type: new Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shiftin…
用离线重要性采样实现分布匹配，为LLM强化学习提供新解法，论文技术细节扎实。
arXiv:2605.17295v1 Announce Type: new Abstract: Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solutio…
提出GAMMA方法，实现任意预算下大语言模型混合精度量化的全局比特自动分配，无需量化感知训练。
arXiv:2605.18475v1 Announce Type: new Abstract: Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) …
深度神经网络泛化理论新视角，揭示点态泛化机制，突破传统平均泛化分析局限。
arXiv:2605.18598v1 Announce Type: new Abstract: We address the fundamental question of why deep neural networks generalize by establishing a pointwise…
银行每年处理数百万份欺诈报告，这个AI代理通过对话、探询和智能路由，精准分流客户至专家团队，解决人工流程慢和压力大的痛点。
arXiv:2605.16268v1 Announce Type: cross Abstract: Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it c…
多轮对话评估揭示AI在动物福利对齐上的隐蔽失败，压力下模型会背离初始立场。
arXiv:2605.16301v1 Announce Type: cross Abstract: Single-turn benchmarks such as AnimalHarmBench (AHB) have established important baselines for measur…
首个泛化感知基准评估GPU内核优化代理，推动自动调优技术落地。
arXiv:2605.16819v1 Announce Type: cross Abstract: GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing hi…
大规模LLM训练推理性能模拟新方案，细粒度统一模拟器精准优化设计空间。
arXiv:2605.17164v1 Announce Type: cross Abstract: Deploying large-scale LLM training and inference with optimal performance is exceptionally challengi…
从算子代数出发，NOETHER框架系统化发现形变模式，驱动物理、ML与查询优化创新。
arXiv:2605.17390v1 Announce Type: cross Abstract: Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly r…
从零复现GPT核心机制，基于PyTorch实现简洁自回归语言模型，AI学习者必读的底层论文教程。
arXiv:2605.17398v1 Announce Type: cross Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive langu…
提出VeriCache方法，将有损KV Cache转化为无损LLM推理，提升模型效率与精度。
arXiv:2605.17613v1 Announce Type: cross Abstract: The large size of the KV cache has become a major bottleneck for serving LLMs with increasing contex…