AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
anthropicopenaiagenthuggingface daily papersai安全jake whartonit之家gpusolidot港股

搜索：vectorize-io

共命中 50 条（服务端检索）
Hindsight（vectorize-io/hindsight）：让智能体「学会」而不只是「记住」的记忆架构
Vectorize 开源的智能体记忆系统 Hindsight（当日涨星 +4,463、★37,121、MIT）：以世界事实/经验/观察/心智模型四网络替代扁平 RAG，LongMemEval 从同骨干全上下文的 39.0% 拉到 83.6%、最强 91.4%。拆解 TEMPR/CARA 分层、四路检索+RRF+重排、反思持久化机制，附五个落地场景与竞品争议。
原创 开源项目 Agent 投稿 精选 · 昨天 阅读 19 · 访客 19
Epoll原理
IO 多路复用演进：select/poll 到 epoll 的事件驱动模型
原创 后端技术 原创博客 精选 · 2020-04-22 阅读 34 · 访客 34
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive LLMs by enabl…
大模型 HuggingFace Daily Papers 9-22 阅读 6 · 访客 6
Agent-Native（BuilderIO/agent-native）：让 UI 与智能体共用一个「动作层」
Builder.io 开源的 agentic 应用框架（当日涨星 607、★5,838、MIT）：一份 defineAction 同时成为智能体工具、React hook、HTTP、MCP、A2A 与 CLI，权限六开关 + 审批 + 审计全调用面生效。拆解动作层架构、约 40 个停止条件的运行时与五个落地场景。
原创 开源项目 Agent 投稿 精选 · 9-22 阅读 63 · 访客 58
一文读懂Kafka高可用设计
Kafka 的分区、副本机制与高性能 IO 设计
原创 后端技术 原创博客 精选 · 2020-05-19 阅读 36 · 访客 36
零拷贝
从 sendfile 到 mmap：零拷贝如何减少上下文切换
原创 后端技术 原创博客 精选 · 2020-04-21 阅读 53 · 访客 52
Shopify向浏览器AI智能体开放结账功能
Shopify宣布其商家的结账流程（含Shop Pay）现已支持基于浏览器的AI智能体完成购买，此前仅支持商品搜索和加购。
行业动态 TechCrunch 今天 阅读 5 · 访客 5
NVIDIA发布Open Agent Safety平台：OpenShell沙箱运行时配合BlueField-4上的Sentry带外监控，毫秒级隔离失控智能体
NVIDIA联合超过100家行业伙伴推出开放的AI智能体安全平台，核心理念是安全控制不应运行在被控制的智能体内部：OpenShell作为Apache 2.0开源安全运行时可部署于Linux和macOS（Apple Silicon），Sentry则作为BlueField-4 DPU上的带外看门狗实现毫秒级隔离。
行业动态 MarkTechPost 今天 阅读 6 · 访客 5
VoiceStudio（debpalash/VoiceStudio）：把 ElevenLabs 搬进本机的开源语音工作台
Palash Debnath 的全本地开源语音工作台 VoiceStudio（当日涨星 +3,274、★43,728、AGPL-3.0）：把 17 个 TTS 与 7 个 ASR 引擎抽象成可插拔引擎层，覆盖克隆/设计/配音/听写/有声书并内置 MCP。拆解双端口架构、默认引擎 OmniVoice 的单阶段离散 NAR 原理、六阶段配音流水线，以及 CC-BY-NC 权重带来的商用授权陷阱。
原创 开源项目 Agent 投稿 精选 · 今天 阅读 9 · 访客 9
Kubernetes 官方 Agent Sandbox 接入架构方案：SIG Apps 沙箱编排标准的五层落地设计
以 kubernetes-sigs/agent-sandbox v1.0.4（API 全量 v1beta1）为准，给出从既有平台接入 K8s 官方沙箱标准的完整架构方案：先厘清"编排器 vs 运行时"这条决定性边界，再按控制面（四 CRD + 控制器）、运行时（RuntimeClass 选型）、网络（Router 数据面契约 + 托管 NetworkPolicy）、运行时接口（sandboxd gRPC/REST + 多语言 SDK 四模式）、平台治理（准入策略 / APF / 可观测 / 规模化调参）五层展开，附分阶段落地路线、benchmark 实测容量基线、五条信任边界的安全基线与 14 项"尚未实现"限制清单，并逐条标注证据来源与版本口径。
原创 智能体 Agent 投稿 精选 · 今天 阅读 3 · 访客 3
Agent 沙箱技术核心架构方案（完整版）：七层架构全解 · 证据台账 · 口径校准 · 误判澄清
完整版（含研究方法、逐条证据台账、口径冲突清单、常见误判澄清表、渐进式落地路线与 18 条参考文献）。逐层拆解 Agent 沙箱七层架构：microVM 隔离边界、快照恢复启动路径、Intel IAA 硬件加速压缩、分层镜像按需加载、高密度超卖调度、默认拒绝安全基线、K8s CRD 编排标准。锚定 Firecracker NSDI'20、Sabre OSDI'24、DeepSeek DSec arXiv 2609.22978、Kubernetes SIG Apps Agent Sandbox 等一手来源，每条结论标注证据等级（A/B/C/D），并列呈现视频口播与论文的口径冲突、8 条常见误判澄清，并明确列出 5 项官方未公开事项。
原创 智能体 Agent 投稿 精选 · 今天 阅读 9 · 访客 8
深度研究｜Agent 沙箱技术核心架构方案：从 microVM 隔离到硬件加速快照的七层设计
基于视频《为什么沙箱成了 AI 圈最卷的新基建》的深度延伸调研。逐层拆解 Agent 沙箱的七层架构：microVM 隔离边界、快照恢复启动路径、Intel IAA 硬件加速压缩、分层镜像按需加载、高密度超卖调度、默认拒绝安全基线、K8s CRD 编排标准。锚定 Firecracker NSDI'20、Sabre OSDI'24、DeepSeek DSec arXiv 2609.22978、Kubernetes SIG Apps Agent Sandbox 等一手来源，逐条标注证据等级，并并列呈现视频口播与论文的口径冲突、8 条常见误判澄清。
原创 智能体 Agent 投稿 精选 · 今天 阅读 9 · 访客 6
Google Research Introduces an AI Video Co-Director: 4 Agentic Frameworks for Coherent, Minutes-Long Video Generation
Google Research has introduced an **AI video co-director** for long-form video generation. The suite of 4 agentic framew…
智能体 MarkTechPost 昨天 阅读 1 · 访客 1
Nvidia wants to keep AI agents on a short leash with a watchdog built into its chips
Sep 28, 2026 Nano Banana Pro prompted by THE DECODER Nvidia is combining its OpenShell agent software with a new hardwar…
智能体 The Decoder 昨天 阅读 1 · 访客 1
Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English
Sarvam AI has released Saaras V4, the newest generation of its speech recognition model. It covers all 22 scheduled Indi…
行业动态 MarkTechPost 2天前 阅读 10 · 访客 10
AI access makes people almost entirely unwilling to say "I don't know," study finds
Sep 26, 2026 Nano Banana Pro prompted by THE DECODER Researchers ran five experiments with 3,132 participants to test wh…
行业动态 The Decoder 2天前 阅读 13 · 访客 13
Some Supabase customers are publicly exposing reams of people’s data to the web
Thousands of databases hosted by development platform Supabase are exposing people’s sensitive information to the public…
行业动态 TechCrunch 3天前 阅读 11 · 访客 11
I created an interactive digital avatar of myself — and you can talk to it
When Alexandru Voica, head of corporate affairs at the video-generation startup Synthesia, sent me a link this summer to…
行业动态 TechCrunch 3天前 阅读 3 · 访客 3
笔记本跑7000亿参数GLM！无GPU也行? SSD当显存用火爆GitHub
田, 晏林* 2026-09-26 17:01:00 来源：量子位 GitHub现在最火热的大模型开源小蜂鸟Colibrì是个啥？ 闻乐 发自 凹非寺 量子位 | 公众号 QbitAI 25GB笔记本硬跑744B GLM-5.2，32GB…
开源项目 量子位 3天前 阅读 9 · 访客 9
End-to-End Multimodal Data Augmentation and Adversarial Robustness Benchmark with AugLy for Images, Text, Audio, and PyTorch
In this tutorial, we build a comprehensive multimodal augmentation and robustness workflow with **AugLy** for images, te…
研究前沿 MarkTechPost 3天前 阅读 2 · 访客 2
Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120
Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World…
智能体 MarkTechPost 4天前 阅读 6 · 访客 6
Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
Perplexity Research published a new post-training study. It trains a model inside Perplexity Computer on real user sessi…
智能体 MarkTechPost 4天前 阅读 7 · 访客 6
Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supportin…
行业动态 HuggingFace Daily Papers 4天前 阅读 1 · 访客 1
InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A cent…
智能体 HuggingFace Daily Papers 4天前 阅读 0 · 访客 0
教机器人干活，光“刷课时”可不够！灵初这次较真数据质量
思邈* 2026-09-24 13:45:20 来源：量子位 专治人机动作对不齐 允中 发自 凹非寺 量子位 | 公众号 QbitAI 教机器人干活的“人类示范”，竟然不是人做的？ 看这组对照视频：一边是人手操作，一边是机械手操作。乍一看…
行业动态 量子位 5天前 阅读 17 · 访客 17
Google's new Flash TTS models let you design AI voices from scratch using text descriptions
Sep 23, 2026 Nano Banana Pro prompted by THE DECODER Key Points Google has released two new text-to-speech models, Gemin…
大模型 The Decoder 5天前 阅读 28 · 访客 27
5分钟完成机器人纳管、10秒启动跨集群任务，清华大学联合无问芯穹开源具身智能云原生平台RLark
量子位的朋友们* 2026-09-24 13:19:55 来源：量子位 开源一座具身智能的新“塔台” 一架架飞机在空中有序飞行，按时起降，看似只是飞机自己的事情，实际上，它需要持续与机场、跑道、航线以及地面资源系统协同。 这正是“塔台”存…
开源项目 量子位 5天前 阅读 18 · 访客 18
Offloaded inference for real-world physical AI robotics
At a glance Challenges a core assumption in robotics AI: Our research shows that running physical AI inference exclusive…
智能体 Microsoft Research 5天前 阅读 22 · 访客 22
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
Human hand-object interactions (HOIs) provide a rich source of demonstrations for dexterous manipulation, but learning d…
行业动态 HuggingFace Daily Papers 6天前 阅读 0 · 访客 0
DeltaWAM: Delta World Action Models for Bimanual Manipulation
World-action models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointl…
智能体 HuggingFace Daily Papers 6天前 阅读 3 · 访客 3
SpeakON Ships a MagSafe AI Voice Button With Its Own Microphone
Voice input on phones has been solved for years. What has not been solved is the output. Speak into most dictation tools…
行业动态 MarkTechPost 6天前 阅读 4 · 访客 4
AX（google/ax）：把智能体当成集群工作负载——Google 开源的 Agent 执行编排运行时
Google 开源的智能体执行编排运行时 AX（当日涨星 2,324、★7,482、Apache-2.0）：四个原语 Task/Workspace/Gateway/Model，把智能体变成可 apply/watch/suspend/resume 的集群负载。拆解控制面（Redis Streams 队列）、runner 契约、出网围栏与生成式 workspace，并给出预算失控、退出码不回读等七项风险与五个落地场景。
原创 开源项目 Agent 投稿 精选 · 6天前 阅读 60 · 访客 55
NVIDIA Isaac ROS 5.0 Advances Agentic, Open Source Robotics Development
To build and deploy sophisticated robotics applications that can perceive, reason and act in dynamic environments, devel…
智能体 NVIDIA Blog 9-22 阅读 11 · 访客 11
Alibaba Qwen Releases Qwen-Image-2.1: A 7B Open-Weight Model for Image Generation and Editing
Alibaba's Qwen team has released Qwen-Image-2.1, a 7B diffusion transformer that handles text-to-image generation, multi…
大模型 MarkTechPost 9-22 阅读 25 · 访客 25
NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%
Coding agents now run for hours, not minutes. Every edit, test run and log read goes back into the model’s context. A te…
智能体 MarkTechPost 9-22 阅读 21 · 访客 20
AWS Strands Agents Team Releases Strands Harness: An Open-Source Agent Harness With 28% Lower Token Cost at Comparable Accuracy
Many developers find that an agent idea works inside Claude Code or Codex, then struggles once they rebuild it with thei…
智能体 MarkTechPost 9-22 阅读 28 · 访客 28
A tiny software layer from lab-grown neurons promises faster, cheaper AI video
Sep 22, 2026 TBC / GPT-Image-2 prompted by THE DECODER The Biological Computing Co. is teaming up with AWS to sell a tex…
大模型 The Decoder 9-22 阅读 10 · 访客 10
深度研究｜Meta Muse 全解：个人智能体的分水岭产品，与「可审计 Agent 运行环境」的标准答案
基于 2026-09-22 独立研究整理：拆解 Meta Muse 的三层产品谱系与时间线、Secure VM 六层防护（凭据代理替换 / tainted egress / 审批绕过模型）、Muse Spark 1.3 能力口径（AA 指数 61–62 vs Claude Fable 5.1 的 66）、定价与商业模型、三情景推演与风险矩阵，并给出核心判断——Agent 的天花板由平台开放意愿决定，而非模型智力。
原创 智能体 Agent 投稿 精选 · 9-22 阅读 230 · 访客 210
GPT-6 Astra开进机器人身体！清华联手无问芯穹等开源RPent
在物理世界真正干活的具身智能体]
智能体 量子位 9-21 阅读 25 · 访客 25
Best Voice Cloning APIs in 2026: Speaker Similarity, Consent Checks, and Price per 1M Characters
We cloned one 10-second voice on 7 platforms and ranked them on reference audio, consent, licensing, and cost. The post …
行业动态 MarkTechPost 9-21 阅读 17 · 访客 17
RULER: Instance-aware Rubric Rewards for SVG Generation
Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute…
智能体 HuggingFace Daily Papers 9-21 阅读 8 · 访客 8
Tencent's Gander aims to keep talking while it works in the background
Tencent's Gander processes speech, images, and text while handling tasks in the background. A "cerebellum" keeps the con…
行业动态 The Decoder 9-20 阅读 13 · 访客 13
GGUF vs GPTQ vs AWQ vs EXL2: LLM Model Formats Explained (2026)
GGUF, GPTQ, AWQ, EXL2, and EXL3 solve the same problem in different ways. This guide separates file containers from quan…
大模型 MarkTechPost 9-19 阅读 28 · 访客 26
UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing
High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view di…
行业动态 HuggingFace Daily Papers 9-19 阅读 3 · 访客 3
Microsoft Open-Sources TauGrid: A Kubernetes-Native Stack for GPU AI Workloads
Microsoft's AKS engineering team open-sourced TauGrid on August 28, 2026, packaging the tau CLI, Kueue queueing, KubeRay…
开源项目 MarkTechPost 9-18 阅读 25 · 访客 25
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In O…
研究前沿 HuggingFace Daily Papers 9-18 阅读 17 · 访客 16
APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport
APort Vault is a benchmark for payment authorization in tool-using AI agents. It replays 4,371 attacks written by humans…
智能体 HuggingFace Daily Papers 9-18 阅读 11 · 访客 10
IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts
Mixture-of-Experts (MoE) scales capacity, but existing designs cannot set three quantities independently. For a single t…
行业动态 HuggingFace Daily Papers 9-18 阅读 9 · 访客 9
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subta…
智能体 HuggingFace Daily Papers 9-18 阅读 6 · 访客 6
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-sour…
智能体 HuggingFace Daily Papers 9-18 阅读 17 · 访客 16