TEMPORAL ARCHIVE

时间线归档

共 1924 篇文章;当前第 32 / 39 页

2026 年

50 篇

二月

50
11
GLM-OCR:面向复杂文档理解的多模态OCR模型
[HN] GLM-OCR 多模态
arrow_forward
11
智谱AI发布GLM-5大模型并上线Z.ai平台
[HN] hacker_news
arrow_forward
11
Git Worktree 与 Claude Code 实现多终端并发开发
[Note] Git Worktree Claude Code
arrow_forward
11
Folo:支持AI摘要与多端同步的开源信息阅读器
[Note] Folo 开源项目
arrow_forward
11
Anagent For Enhancing Scientific Table & Figure Analysis
[ArXiv] Anagent 多智能体
arrow_forward
11
AI 核心术语解析:从神经网络原理到词嵌入与潜空间
[Note] 神经网络 词嵌入
arrow_forward
11
[AINews] Qwen Image 2 and Seedance 2
[Blog] Qwen Image 2 Seedance 2
arrow_forward
11
AI Design-to-Code 的两个根本问题与解法
[Note] Design-to-Code D2C
arrow_forward
11
Transformer模型在低信噪比时间序列预测中的统计基准测试
[ArXiv] arxiv cs.LG
arrow_forward
11
Moltbook 漏洞:自进化 AI 社会中 Anthropic 安全机制失效
[ArXiv] Anthropic AI 安全
arrow_forward
11
Hybrid Responsible AI-Stochastic Approach for SLA Compliance in Multivendor 6G Networks
[ArXiv] 6G网络 SLA合规
arrow_forward
11
CoFEH:LLM驱动的协同贝叶斯特征工程框架
[ArXiv] arxiv cs.LG
arrow_forward
11
Code2World: A GUI World Model via Renderable Code Generation
[ArXiv] arxiv cs.CV
arrow_forward
11
Agent-to-agent collaboration: Using Amazon Nova 2 Lite and Amazon Nova Act for multi-agent systems
[Blog] Multi-Agent Amazon Bedrock
arrow_forward
11
Tambo 1.0:开源 AI Agent 工具包支持渲染 React 组件
[HN] AI Agent React
arrow_forward
10
鲁棒性是函数而非数值:基于视觉驾驶的OOD鲁棒性因子化研究
[ArXiv] OOD鲁棒性 视觉驾驶
arrow_forward
10
自动推理检查重写聊天机器人的实现架构
[Blog] 自动推理 聊天机器人
arrow_forward
10
后端聚合技术如何支撑千兆瓦级AI集群Prometheus构建
[Blog] blogs_podcasts
arrow_forward
10
亚马逊利用 Nova 模型自动化新履约中心运营就绪测试
[Blog] Amazon Nova Amazon Bedrock
arrow_forward
10
The Little Learner:通往深度学习的直线路径
[HN] 深度学习 机器学习
arrow_forward
10
New Relic NOVA:基于AWS的生成式AI效能引擎架构与实践
[Blog] 生成式 AI AWS
arrow_forward
10
Iberdrola 如何利用 Amazon Bedrock AgentCore 优化 ServiceNow IT 运营
[Blog] Amazon Bedrock AgentCore
arrow_forward
10
Data Science and Technology Towards AGI Part I: Tiered Data Management
[ArXiv] AGI 数据管理
arrow_forward
10
ARO:面向大模型矩阵优化的新视角
[ArXiv] 矩阵优化 ARO
arrow_forward
10
Amazon Nova Sonic 实时语音助手与级联架构对比
[Blog] Amazon Nova 实时语音
arrow_forward
10
LangChain实战:结合Memory与OutputParser构建有记忆的结构化助手
[Note] LangChain LLM
arrow_forward
10
Clawe:面向智能体团队的开源Trello替代方案
[HN] hacker_news
arrow_forward
10
Claude Code Agent Teams多实例协作原理与主流框架对比
[Note] juejin
arrow_forward
10
利用全栈模板加速开发基于Amazon Bedrock AgentCore的应用
[Blog] Amazon Bedrock AgentCore
arrow_forward
10
Livedocs:面向数据分析的AI原生笔记本
[HN] Livedocs AI原生
arrow_forward
10
大语言模型无法独立攻克癌症的局限性分析
[Blog] LLM 癌症研究
arrow_forward
10
Showboat与Rodney发布:让AI Agent演示其构建成果
[HN] AI Agent Showboat
arrow_forward
10
Rowboat:将工作转化为知识图谱的AI助手
[HN] AI 助手 知识图谱
arrow_forward
10
GEBench:将图像生成模型评估为GUI环境的基准
[ArXiv] GEBench GUI生成
arrow_forward
10
前GitHub CEO推出面向AI代理的新开发者平台
[HN] GitHub Nat Friedman
arrow_forward
10
下一代验证码:利用认知差异防御GUI智能体
[ArXiv] arxiv cs.LG
arrow_forward
10
ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
[ArXiv] ANCRe 深度学习
arrow_forward
10
前沿AI模型在KPI压力下违反伦理约束的比例达30%至50%
[HN] hacker_news
arrow_forward
10
Qwen-Image-2.0:专业信息图表与逼真照片生成
[HN] Qwen Qwen-Image-2.0
arrow_forward
10
LLM 作为语言编译器:Fortran 对编程未来的启示
[HN] LLM 编译器
arrow_forward
10
AI智能体发展预测:未来八个月的技术演进与挑战
[HN] AI 智能体 LLM
arrow_forward
10
Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model
[HN] Mistral STT
arrow_forward
10
针对LLM服务框架而非模型的延迟型拒绝服务攻击研究
[ArXiv] arxiv cs.CR
arrow_forward
10
Mistral Voxtral Mini 4B 浏览器端实时语音 Rust 实现
[HN] Mistral Voxtral
arrow_forward
10
MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation
[ArXiv] arxiv cs.LG
arrow_forward
10
LQA:面向边缘端视觉语言模型的轻量级量化自适应框架
[ArXiv] VLM 边缘计算
arrow_forward
10
Harpoon:面向条件表格扩散模型的广义流形引导
[ArXiv] 扩散模型 表格数据
arrow_forward
09
语言模型对激活引导攻击的内生抗性研究
[ArXiv] 激活引导 内生抗性
arrow_forward
09
智能体不确定性研究揭示过度自信问题
[ArXiv] AI Agents 不确定性
arrow_forward
09
学习大模型神经元激活的生成式元模型
[ArXiv] 神经元激活 生成式模型
arrow_forward